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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    forcement
    -0.06
    ائية
    -0.06
     oe
    -0.06
    nect
    -0.06
    ARATION
    -0.06
     LEGO
    -0.06
    änge
    -0.06
    tee
    -0.06
     ();↵↵
    -0.06
    cards
    -0.06
    POSITIVE LOGITS
    .syn
    0.07
     основных
    0.07
     Bay
    0.07
     Бел
    0.07
    Access
    0.07
    .ButterKnife
    0.06
    ,,,,,,,,
    0.06
     hiển
    0.06
     Erotik
    0.06
     τελ
    0.06
    Act Density 0.029%

    No Known Activations