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

    Neuronpedia

    INDEX
    Explanations

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (thread
    -0.07
    periences
    -0.06
     warranted
    -0.06
     ông
    -0.06
    aper
    -0.06
    忙
    -0.06
    并
    -0.06
     curs
    -0.06
     binary
    -0.06
    .pk
    -0.06
    POSITIVE LOGITS
    .password
    0.07
     JSONException
    0.07
     eco
    0.07
     HMAC
    0.07
    clusters
    0.07
     případ
    0.07
    rowsable
    0.06
     ADS
    0.06
    .Scan
    0.06
    予約
    0.06
    Act Density 0.019%

    No Known Activations