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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yć
    -0.07
    SAME
    -0.07
    …I
    -0.07
    AnimationFrame
    -0.07
    談
    -0.07
    །
    -0.06
    please
    -0.06
     данном
    -0.06
    ")+
    -0.06
    ergarten
    -0.06
    POSITIVE LOGITS
     הש
    0.07
    .op
    0.07
     owner
    0.07
    �
    0.07
    打败
    0.06
     компания
    0.06
    רוע
    0.06
    مواجه
    0.06
     sidew
    0.06
     Tight
    0.06
    Act Density 0.004%

    No Known Activations