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

    Neuronpedia

    INDEX
    Explanations

    numerical values or sequences related to data or coding

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

    Timestamps with arrow separators

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.77
    исленность
    -0.58
    rawDesc
    -0.57
    …
    -0.52
     “
    -0.51
    chées
    -0.51
    (@"%@",
    -0.50
     ví
    -0.48
    UrlResolution
    -0.47
    +};
    -0.47
    POSITIVE LOGITS
     Anſ
    0.89
    ReusableCell
    0.84
     FontWeight
    0.80
     myſelf
    0.79
     Efq
    0.79
    المناصب
    0.77
     houſe
    0.77
    ConstraintMaker
    0.76
    bufio
    0.74
     متعلقه
    0.72
    Act Density 0.111%

    No Known Activations