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

    Neuronpedia

    INDEX
    Explanations

    invincibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     branche
    -0.09
     periode
    -0.08
    提前
    -0.08
     montant
    -0.08
    periode
    -0.08
     sombre
    -0.08
     retrospect
    -0.08
     proximal
    -0.07
     हस्त
    -0.07
     فرق
    -0.07
    POSITIVE LOGITS
    ত্ব
    0.09
    ibility
    0.08
     �
    0.08
     практически
    0.08
    Except
    0.08
     immune
    0.08
    Aura
    0.08
     defense
    0.08
    ously
    0.08
    ити
    0.07
    Act Density 0.009%

    No Known Activations