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

    Neuronpedia

    INDEX
    Explanations

    technical terms and variables related to shadows and lighting in programming code

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

    Floating point numbers or math expressions

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     int
    -1.00
    int
    -0.99
     Int
    -0.66
    Int
    -0.63
    INT
    -0.54
    toInt
    -0.53
     parseInt
    -0.52
     INT
    -0.51
    intValue
    -0.50
    jint
    -0.47
    POSITIVE LOGITS
    клопе
    0.84
     itſelf
    0.79
    =.
    0.77
    saraba
    0.77
     {:.
    0.74
     $-.
    0.74
     myſelf
    0.72
     atof
    0.71
     /\.(
    0.70
    はじめに
    0.70
    Act Density 0.526%

    No Known Activations