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

    Neuronpedia

    INDEX
    Explanations

    /H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _again
    -0.08
     vulgar
    -0.07
     hombres
    -0.06
    \Config
    -0.06
     العن
    -0.06
     سیاسی
    -0.06
     solid
    -0.06
     Ian
    -0.06
    集合
    -0.06
    _known
    -0.06
    POSITIVE LOGITS
    ịp
    0.07
    xBA
    0.07
    events
    0.07
    /swagger
    0.07
    ZX
    0.06
    ο
    0.06
    ło
    0.06
     toppings
    0.06
    JSONException
    0.06
     Musk
    0.06
    Act Density 0.002%

    No Known Activations