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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ymi
    -0.08
    анти
    -0.07
    яв
    -0.07
     된다
    -0.07
    llu
    -0.06
    طور
    -0.06
     ^.
    -0.06
    369
    -0.06
     milli
    -0.06
    дяки
    -0.06
    POSITIVE LOGITS
     kịp
    0.06
     Regards
    0.06
    _male
    0.06
     linspace
    0.06
     szer
    0.05
    (Dictionary
    0.05
     送
    0.05
     pat
    0.05
     GUIContent
    0.05
    .sqrt
    0.05
    Act Density 0.019%

    No Known Activations