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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    范围
    -0.08
    _domains
    -0.08
     ಘ
    -0.08
    ovid
    -0.07
    ाक्ष
    -0.07
     Eternal
    -0.07
    anzeigen
    -0.07
    /releases
    -0.07
    ibling
    -0.07
     trist
    -0.07
    POSITIVE LOGITS
     રીત
    0.11
     सही
    0.10
     correct
    0.09
     الطريقة
    0.09
     тәс
    0.09
     optimal
    0.09
     ngendlela
    0.09
     правиль
    0.09
     صحیح
    0.09
     benar
    0.09
    Act Density 0.033%

    No Known Activations