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

    Neuronpedia

    INDEX
    Explanations

    data chunks/processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bite
    -1.03
    Bite
    -1.01
     bites
    -0.98
     Bite
    -0.96
    bites
    -0.89
     purpoſe
    -0.87
     juſ
    -0.84
     itſelf
    -0.84
     reaſon
    -0.83
     chunk
    -0.82
    POSITIVE LOGITS
    ,
    0.72
    /***/
    0.58
    GEBURTSDATUM
    0.58
    KommentareTeilen
    0.55
     <<<<<<<<<<<<<<
    0.55
    !*\
    0.54
    .
    0.54
    createClass
    0.53
     OnInit
    0.53
    :
    0.52
    Act Density 0.168%

    No Known Activations