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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Como
    -0.08
    Como
    -0.06
     Charity
    -0.06
    lucent
    -0.06
    Cool
    -0.06
    міну
    -0.06
     Blood
    -0.06
     perfor
    -0.06
    emplates
    -0.06
     خدم
    -0.06
    POSITIVE LOGITS
     достаточно
    0.07
    .Toggle
    0.07
    231
    0.06
     Legislation
    0.06
    ườn
    0.06
    τια
    0.06
    َي
    0.06
     Bali
    0.06
    0.06
    ніш
    0.06
    Act Density 0.002%

    No Known Activations