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

    Neuronpedia

    INDEX
    Explanations

    webpack compilation and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ന്
    -0.79
     ratification
    -0.73
     ribos
    -0.71
     kênh
    -0.71
     Addis
    -0.69
     worrying
    -0.67
     Herzen
    -0.67
    Související
    -0.66
     Bezir
    -0.65
    บาล
    -0.65
    POSITIVE LOGITS
     compilation
    0.94
     reasons
    0.84
    WEBPACK
    0.83
     frit
    0.82
    compilation
    0.82
    wpa
    0.82
    charpe
    0.81
    न्स
    0.79
    фици
    0.79
    Fullscreen
    0.79
    Act Density 0.031%

    No Known Activations