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

    Neuronpedia

    INDEX
    Explanations

    itud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    란
    -0.07
    幼
    -0.07
    اث
    -0.06
    бав
    -0.06
     Dota
    -0.06
    BH
    -0.06
    bulan
    -0.06
    '&&
    -0.06
    ???
    -0.06
    كام
    -0.06
    POSITIVE LOGITS
    ait
    0.07
     ft
    0.07
    raid
    0.06
    (always
    0.06
    (",")↵
    0.06
    Cache
    0.06
    _secondary
    0.06
    (graph
    0.06
     radial
    0.06
    RequestMethod
    0.06
    Act Density 0.001%

    No Known Activations