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

    Neuronpedia

    INDEX
    Explanations

    exclamations and expressions of emphasis

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

    finding the closest value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.44
     thorns
    -0.40
     Bentham
    -0.40
     miras
    -0.39
    tól
    -0.36
    %)$
    -0.36
     někdo
    -0.36
    投稿日
    -0.35
     konser
    -0.35
     člověk
    -0.35
    POSITIVE LOGITS
    penup
    0.75
    flashdata
    0.59
     Biôgrafia
    0.55
    ↹
    0.54
     Мексичка
    0.54
    ulemon
    0.48
    EndInit
    0.47
    EndGlobalSection
    0.45
    ंदीखरीदारी
    0.44
    scriptcase
    0.44
    Act Density 0.000%

    No Known Activations