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

    Neuronpedia

    INDEX
    Explanations

    regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。しかし
    -0.07
     pozor
    -0.06
    ussia
    -0.06
    _gap
    -0.06
     الأن
    -0.06
     birey
    -0.06
    \\.
    -0.06
     Croat
    -0.06
    ası
    -0.06
     pray
    -0.06
    POSITIVE LOGITS
     GUID
    0.07
    ICIAL
    0.07
    ザー
    0.07
    洗
    0.07
    #aa
    0.07
     regularization
    0.06
     panorama
    0.06
     formulations
    0.06
    (delete
    0.06
    异常
    0.06
    Act Density 0.014%

    No Known Activations