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

    Neuronpedia

    INDEX
    Explanations

    text elements related to legal or technical discussions

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

    Text within brackets

    np_acts-logits-general · gemini-2.0-flash

    brackets and specific characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.70
    EDEFAULT
    -0.62
    存于互联网档案馆
    -0.62
    esterday
    -0.62
     leaſt
    -0.62
    nent
    -0.61
     Jefus
    -0.60
    وانید
    -0.60
     becauſe
    -0.60
     purpoſe
    -0.59
    POSITIVE LOGITS
     HomeComponent
    0.54
    ラク
    0.45
     UIFont
    0.45
     tué
    0.43
     createSlice
    0.43
    ectady
    0.43
    LITERAL
    0.41
     vPvB
    0.40
    lake
    0.40
    rikes
    0.39
    Act Density 0.112%

    No Known Activations