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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions and their outcomes

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

    tokens after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.58
    ์ตูน
    -0.44
     Signalez
    -0.41
    Kjelder
    -0.41
    mariage
    -0.39
    createClass
    -0.39
    replyreport
    -0.39
    Bakgrunnsstoff
    -0.38
    OrNil
    -0.38
    Ƚ
    -0.37
    POSITIVE LOGITS
    <?
    0.46
    Пото
    0.44
    MLLoader
    0.42
    シュ
    0.41
    delwed
    0.40
     Presently
    0.40
    sch
    0.40
     yyr
    0.39
    umo
    0.39
    DllImport
    0.39
    Act Density 0.091%

    No Known Activations