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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cosplay
    -0.08
    Long
    -0.08
    ||
    -0.08
    ঙ্গে
    -0.08
    Stripe
    -0.08
     lifestyles
    -0.07
     spas
    -0.07
    Climate
    -0.07
    Diffuse
    -0.07
     glauben
    -0.07
    POSITIVE LOGITS
    .serialize
    0.08
     параметры
    0.08
     влад
    0.08
     deg
    0.08
    :Set
    0.08
     маълум
    0.07
     Zin
    0.07
     информацию
    0.07
     பய
    0.07
     degener
    0.07
    Act Density 0.046%

    No Known Activations