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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and discussions related to research methodologies

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

    parentheses followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    citations with years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.71
    kloped
    -0.68
    ніципа
    -0.67
     Wikimédia
    -0.64
    ":[{
    -0.58
     ſche
    -0.57
     cucchiaio
    -0.56
     InputDecoration
    -0.56
     Commencez
    -0.53
    исленность
    -0.52
    POSITIVE LOGITS
     forthcoming
    0.83
     unpublished
    0.80
    unpublished
    0.73
    personal
    0.65
     recent
    0.65
     personal
    0.65
    forth
    0.63
     cited
    0.60
     undated
    0.59
    DebuggerNonUser
    0.58
    Act Density 0.262%

    No Known Activations