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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sometimes
    -0.07
    }"
    -0.07
    _app
    -0.07
    .like
    -0.07
     badge
    -0.06
     multiprocessing
    -0.06
    __
    -0.06
     갤
    -0.06
    OutOfBounds
    -0.06
     About
    -0.06
    POSITIVE LOGITS
     示
    0.07
     جان
    0.06
     ド
    0.06
    ικός
    0.06
    	ID
    0.06
    of
    0.06
    اعت
    0.06
     Ner
    0.06
    остью
    0.06
     TOR
    0.06
    Act Density 0.010%

    No Known Activations