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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions and calculations involving mathematical operations

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

    Fractions and exponents

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.75
     createState
    -0.68
     StringTokenizer
    -0.59
    Portale
    -0.58
    脚注の使い方
    -0.58
    IContainer
    -0.56
    WithIOException
    -0.55
    ై
    -0.53
    principalTable
    -0.53
    ftagPool
    -0.52
    POSITIVE LOGITS
     DD
    0.94
     RR
    0.91
     PP
    0.89
     SS
    0.89
     BB
    0.88
     GG
    0.88
     CC
    0.87
     LL
    0.86
     BBB
    0.86
     TT
    0.85
    Act Density 0.903%

    No Known Activations