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

    Neuronpedia

    INDEX
    Explanations

    produce

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    原则
    -0.07
    аем
    -0.07
    MBOL
    -0.07
    意見
    -0.07
     neuron
    -0.07
     Cement
    -0.07
    /question
    -0.07
     Developers
    -0.07
    озвращает
    -0.07
    的原因
    -0.07
    POSITIVE LOGITS
     calibration
    0.07
    des
    0.07
    恺
    0.07
     appetite
    0.07
    -inf
    0.07
     battles
    0.07
    atin
    0.07
    .large
    0.06
    靖
    0.06
    ഹ
    0.06
    Act Density 0.025%

    No Known Activations