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

    Neuronpedia

    INDEX
    Explanations

    ut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     курс
    -0.07
    agina
    -0.06
     isl
    -0.06
     Bentley
    -0.06
     heal
    -0.06
     Hague
    -0.06
     captcha
    -0.06
    ciler
    -0.06
     Trials
    -0.06
    ieme
    -0.06
    POSITIVE LOGITS
    supports
    0.07
    pora
    0.07
    thal
    0.06
    ่าจะ
    0.06
    247
    0.06
    monary
    0.06
    (enabled
    0.06
    IMUM
    0.06
    yat
    0.06
    _submenu
    0.06
    Act Density 0.001%

    No Known Activations