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

    Neuronpedia

    INDEX
    Explanations

    references to negative quantities or values

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

    Legal and technical citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    twimg
    -0.49
    Arr
    -0.38
     resourceCulture
    -0.36
    RTGC
    -0.34
    UnusedPrivate
    -0.34
     sûr
    -0.33
    ฎ
    -0.33
    पया
    -0.33
    }{*}{}
    -0.33
    inv
    -0.33
    POSITIVE LOGITS
    contentLoaded
    0.57
    $_['
    0.57
    awtextra
    0.53
    IndentedString
    0.52
     indisponible
    0.51
    WithIOException
    0.50
    RegistryLite
    0.50
    extAlignment
    0.49
    jsxFileName
    0.48
    ConstraintMaker
    0.47
    Act Density 0.106%

    No Known Activations