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

    Neuronpedia

    INDEX
    Explanations

    say file extensions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    и
    -0.08
    ي
    -0.07
     vídeos
    -0.07
    拶
    -0.07
     courier
    -0.07
    \Id
    -0.07
     explor
    -0.07
     Aer
    -0.07
    üğü
    -0.07
     Flam
    -0.07
    POSITIVE LOGITS
    是个
    0.07
     ("
    0.07
    .snap
    0.07
    dığımız
    0.07
    ("""
    0.07
     hidden
    0.07
     כלומר
    0.07
    .Admin
    0.06
    :\\
    0.06
    //'
    0.06
    Act Density 0.005%

    No Known Activations