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

    Neuronpedia

    INDEX
    Explanations

    improved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ろう
    -0.07
     tướng
    -0.06
    ANT
    -0.06
     cant
    -0.06
    $sub
    -0.06
    نب
    -0.06
       ↵    ↵
    -0.06
    _OBJECT
    -0.06
    <byte
    -0.06
    boss
    -0.06
    POSITIVE LOGITS
    대표
    0.06
    umption
    0.06
    _search
    0.06
    Increased
    0.06
    052
    0.06
    anced
    0.06
     photographed
    0.06
    AutoresizingMask
    0.06
    hf
    0.06
     Вс
    0.06
    Act Density 0.006%

    No Known Activations