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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lebih
    -0.08
     недостат
    -0.07
     توص
    -0.07
     قادر
    -0.07
     فاصله
    -0.07
     Strings
    -0.07
     بالاتر
    -0.06
    लग
    -0.06
     eliminar
    -0.06
     başlay
    -0.06
    POSITIVE LOGITS
    ServletContext
    0.06
    -guid
    0.06
     pornografia
    0.06
    ップ
    0.06
    NSMutable
    0.06
    -opening
    0.06
    _probs
    0.06
    ��
    0.05
     enrollment
    0.05
     permutation
    0.05
    Act Density 0.179%

    No Known Activations