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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     full
    -0.07
    (dict
    -0.06
     huz
    -0.06
    랜
    -0.06
     FRE
    -0.06
    俊
    -0.06
    ावन
    -0.06
     промислов
    -0.05
    	handle
    -0.05
     urn
    -0.05
    POSITIVE LOGITS
    _pdu
    0.07
    Prediction
    0.07
    orse
    0.07
    ايش
    0.07
    undred
    0.07
     Antoine
    0.07
    анії
    0.07
    Smarty
    0.07
    ده
    0.06
    ('</
    0.06
    Act Density 0.026%

    No Known Activations