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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NORMAL
    -0.06
     Mam
    -0.06
    LocalizedMessage
    -0.06
    ?>"
    -0.06
    "=>$
    -0.06
     Orta
    -0.06
     Erd
    -0.06
    _apps
    -0.06
     español
    -0.06
    isi
    -0.06
    POSITIVE LOGITS
    /shop
    0.07
    _img
    0.07
    願
    0.07
    aniel
    0.06
    违
    0.06
    ع
    0.06
    ecess
    0.06
     σχ
    0.06
    (sentence
    0.06
    awaii
    0.06
    Act Density 0.033%

    No Known Activations