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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     principale
    -0.08
    ера
    -0.08
    ியான
    -0.08
     Lagos
    -0.07
     تولید
    -0.07
     الش
    -0.07
     levende
    -0.07
     mod
    -0.07
    ราค
    -0.07
    ิเ�
    -0.07
    POSITIVE LOGITS
     accomplishment
    0.10
    wist
    0.09
    finden
    0.09
    wu
    0.09
    ательного
    0.09
     accomplishments
    0.09
    präch
    0.08
    strict
    0.08
    utm
    0.08
    狠
    0.08
    Act Density 0.017%

    No Known Activations