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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .methods
    -0.07
     여기
    -0.07
     налог
    -0.06
     listings
    -0.06
     του
    -0.06
     anomalies
    -0.06
     MENU
    -0.06
     multin
    -0.06
     welfare
    -0.06
     κατα
    -0.06
    POSITIVE LOGITS
    歐
    0.07
     编
    0.06
    /she
    0.06
    欧
    0.06
     عد
    0.06
    °F
    0.06
     زي
    0.06
     паци
    0.06
    }}{{
    0.06
     єв
    0.06
    Act Density 0.003%

    No Known Activations