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

    Neuronpedia

    INDEX
    Explanations

    Japanese characters or words

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

    user input context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.57
    TestingModule
    -0.57
     Infór
    -0.48
     amortecedor
    -0.48
    InputBorder
    -0.46
    ReusableCell
    -0.46
    原始内容
    -0.45
     humanidade
    -0.43
     humanidad
    -0.43
    AndEndTag
    -0.43
    POSITIVE LOGITS
     nakalista
    0.60
     autorytatywna
    0.52
    WriteLiteral
    0.44
    Autoritní
    0.43
     Roads
    0.42
     okuyayım
    0.42
    hithe
    0.42
    Sqft
    0.41
    ✨:
    0.41
    ↵
    0.41
    Act Density 0.000%

    No Known Activations