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

    Neuronpedia

    INDEX
    Explanations

    instances of significant whitespace in text

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

    class constructors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.47
    neté
    -0.39
     stay
    -0.39
     anchor
    -0.39
    MigrationBuilder
    -0.38
     stays
    -0.38
    ynos
    -0.38
     unknownFields
    -0.38
    `}`,
    -0.37
    zös
    -0.36
    POSITIVE LOGITS
    LookAnd
    0.56
     الرياضيه
    0.49
    ContentAsync
    0.46
     bileklik
    0.46
    irvana
    0.44
     pinulongan
    0.43
    SharedDtor
    0.42
    ">//
    0.41
     yelek
    0.41
     invokingState
    0.41
    Act Density 0.006%

    No Known Activations