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

    Neuronpedia

    INDEX
    Explanations

    legal defenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cache
    -0.08
     inter
    -0.08
     legumes
    -0.07
    Cross
    -0.07
    ggio
    -0.07
     Cache
    -0.07
     Cross
    -0.07
    缓存
    -0.07
    .+
    -0.07
    -cache
    -0.07
    POSITIVE LOGITS
     ظروف
    0.10
     الظروف
    0.09
     omstandigheden
    0.09
     unfore
    0.09
    免责
    0.09
     repent
    0.09
     circumstances
    0.09
    constitution
    0.08
     обстоятель
    0.08
     الطبيعية
    0.08
    Act Density 0.049%

    No Known Activations