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

    Neuronpedia

    INDEX
    Explanations

    wrong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proclamation
    -0.07
    ppo
    -0.07
     customizable
    -0.07
     apps
    -0.07
     affirmation
    -0.07
    taf
    -0.07
     padrão
    -0.07
     futuristic
    -0.07
     Walnut
    -0.07
    anato
    -0.07
    POSITIVE LOGITS
     reconsider
    0.08
     असे
    0.08
     revise
    0.08
     insanların
    0.08
    OA
    0.08
    。因此
    0.08
     अशी
    0.07
     காரண
    0.07
    Rede
    0.07
     bzw
    0.07
    Act Density 0.011%

    No Known Activations