Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific types of panel labels and descriptions in a structured document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text snippets before a colon or quotation mark

    np_acts-logits-general · gemini-2.0-flash

    colon after punctuation or label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.75
    ///</
    -0.70
     tartalomajánló
    -0.59
    IContainer
    -0.55
     виправивши
    -0.54
    Vegeu
    -0.53
    DebuggerStep
    -0.51
     term
    -0.50
    ***************/
    -0.49
     Signalez
    -0.49
    POSITIVE LOGITS
    Scénario
    0.61
    FormTagHelper
    0.58
    ptonshire
    0.57
    ագրություններ
    0.56
     InputDecoration
    0.56
    tanleria
    0.54
    KommentareTeilen
    0.54
    MemoryWarning
    0.53
     متعلقه
    0.52
     Endlich
    0.51
    Act Density 0.207%

    No Known Activations