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

    Neuronpedia

    INDEX
    Explanations

    action followed by what it pertains to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aforementioned
    -0.10
    PFN
    -0.09
    ;/*
    -0.08
     HOH
    -0.08
    ataka
    -0.08
    meteor
    -0.08
    torrent
    -0.08
     Mühendis
    -0.08
    PackageName
    -0.07
    &amp
    -0.07
    POSITIVE LOGITS
     somewhat
    0.09
    âĢ²
    0.09
    __
    0.08
     typically
    0.08
     various
    0.08
    âĢĮ
    0.08
     Gin
    0.08
     COPYRIGHT
    0.08
     often
    0.08
    uffs
    0.07
    Act Density 0.077%

    No Known Activations