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

    Neuronpedia

    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CAT
    -0.06
    _calibration
    -0.06
    alert
    -0.06
     Jones
    -0.06
    zier
    -0.06
    yal
    -0.06
     certificates
    -0.06
     pop
    -0.06
     UsersController
    -0.06
    _COLL
    -0.06
    POSITIVE LOGITS
     MOCK
    0.08
     حجم
    0.06
     огля
    0.06
     Роб
    0.06
    λης
    0.06
    %H
    0.06
     Attach
    0.06
     вним
    0.06
    ไป
    0.06
     ارزی
    0.06
    Act Density 0.000%

    No Known Activations