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

    Neuronpedia

    INDEX
    Explanations

    arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wild
    -0.07
     الآن
    -0.07
     kiểm
    -0.07
    อกจาก
    -0.06
    _ComCallableWrapper
    -0.06
     температу
    -0.06
     seas
    -0.06
     вваж
    -0.06
     vidé
    -0.06
     Tu
    -0.06
    POSITIVE LOGITS
     kc
    0.07
     Plugin
    0.07
    _MA
    0.07
    DR
    0.06
    Customers
    0.06
     ί
    0.06
     Aer
    0.06
     substitute
    0.06
     fed
    0.06
    děl
    0.06
    Act Density 0.008%

    No Known Activations