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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     అంటూ
    -0.08
    stan
    -0.08
    という
    -0.08
     gt
    -0.08
    acht
    -0.07
    라는
    -0.07
     dissemin
    -0.07
    dated
    -0.07
     అని
    -0.07
    putable
    -0.07
    POSITIVE LOGITS
    ingerprint
    0.09
    人格
    0.08
     башка
    0.08
    itian
    0.08
     calculators
    0.07
    商品の
    0.07
     पो
    0.07
     ملا
    0.07
     ಉದ್ಯ
    0.07
    0.07
    Act Density 0.021%
    No Known Activations