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
     soaked
    -0.07
     HWND
    -0.07
     Tops
    -0.06
    =str
    -0.06
     яка
    -0.06
    aille
    -0.06
     gồm
    -0.06
     taller
    -0.06
    .MaxValue
    -0.06
    InnerText
    -0.06
    POSITIVE LOGITS
    _TestCase
    0.07
     난
    0.07
     beginners
    0.06
    enção
    0.06
    ического
    0.06
    (balance
    0.06
    [source
    0.06
    _SETTING
    0.06
    scar
    0.06
    odes
    0.06
    Act Density 0.018%

    No Known Activations