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

    Neuronpedia

    INDEX
    Explanations

    deaths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unist
    -0.07
    琔
    -0.07
    璃
    -0.07
    UTF
    -0.07
    镭
    -0.06
    的过程中
    -0.06
    orderId
    -0.06
    структор
    -0.06
    compass
    -0.06
    签署
    -0.06
    POSITIVE LOGITS
     deaths
    0.08
     Doug
    0.07
    脱发
    0.07
    被害
    0.07
     dietary
    0.07
     interventions
    0.07
     vocals
    0.07
     mortality
    0.07
    <?=$
    0.07
     coch
    0.07
    Act Density 0.006%

    No Known Activations