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

    Neuronpedia

    INDEX
    Explanations

    references to variables or values in programming code

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

    val, msgstr, what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.57
    ⤹
    -0.57
     Efq
    -0.51
     betweenstory
    -0.49
     المعيارى
    -0.49
    ViewInit
    -0.48
    beiros
    -0.47
     desmotivaciones
    -0.47
    出版年
    -0.47
    Referències
    -0.46
    POSITIVE LOGITS
     val
    0.94
    val
    0.94
     Val
    0.73
    Val
    0.68
    VAL
    0.65
     VAL
    0.58
    valu
    0.54
     value
    0.53
     valore
    0.52
     valer
    0.51
    Act Density 0.002%

    No Known Activations