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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or numerical patterns

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

    Hexadecimal strings starting with "0x0"

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.68
     surla
    -0.63
     kaarangay
    -0.61
    ⤹
    -0.59
     ModelExpression
    -0.59
    __(/*!
    -0.59
     ब्रेकडाउन
    -0.56
    uxxxx
    -0.56
    MessageOf
    -0.53
    afficheront
    -0.52
    POSITIVE LOGITS
    TabIndex
    0.50
     wasting
    0.45
    結局
    0.44
    Trending
    0.43
     direção
    0.42
    ๆ
    0.42
     menahan
    0.41
     conclusão
    0.41
    本日は
    0.41
     einf
    0.41
    Act Density 0.500%

    No Known Activations