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

    Neuronpedia

    INDEX
    Explanations

    Related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     duke
    -0.07
    zí
    -0.06
     Lord
    -0.06
     Mons
    -0.06
     �
    -0.06
     Mer
    -0.06
     hra
    -0.06
     MD
    -0.06
     knight
    -0.06
     cult
    -0.06
    POSITIVE LOGITS
    adjust
    0.07
    /ph
    0.07
     налог
    0.06
    отов
    0.06
     caching
    0.06
     返回
    0.06
    ีอย
    0.06
    (session
    0.06
     obrig
    0.06
    !=-
    0.06
    Act Density 0.001%

    No Known Activations