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

    Neuronpedia

    INDEX
    Explanations

    catalysts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recourse
    -0.06
     devices
    -0.06
    Great
    -0.06
    cells
    -0.06
     Handbook
    -0.06
    ugged
    -0.06
     cancellation
    -0.06
    \")
    -0.06
    /error
    -0.06
     Clement
    -0.06
    POSITIVE LOGITS
     мощ
    0.09
     صلى
    0.07
    _pressed
    0.06
    대회
    0.06
    abajo
    0.06
     Cata
    0.06
     поля
    0.06
    _FOUND
    0.06
     路
    0.06
    หนด
    0.06
    Act Density 0.048%

    No Known Activations