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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .addObject
    -0.07
    onn
    -0.07
    482
    -0.07
    618
    -0.07
    585
    -0.06
     ///<
    -0.06
    492
    -0.06
    response
    -0.06
     remedy
    -0.06
    oueur
    -0.06
    POSITIVE LOGITS
    TEGR
    0.08
    /↵
    0.08
    /.↵
    0.08
    /-
    0.08
     урож
    0.07
    uma
    0.07
     czas
    0.07
     Phi
    0.07
    ��
    0.07
     větš
    0.07
    Act Density 0.020%

    No Known Activations