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

    Neuronpedia

    INDEX
    Explanations

    literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mozilla
    -0.07
    _requires
    -0.07
    	event
    -0.06
     row
    -0.06
     zakáz
    -0.06
     Только
    -0.06
     ix
    -0.06
    Pont
    -0.06
     ejemplo
    -0.06
    Ace
    -0.06
    POSITIVE LOGITS
     literature
    0.13
    uteur
    0.08
     Literature
    0.08
    لیه
    0.07
    kg
    0.07
     levy
    0.06
    generic
    0.06
     дав
    0.06
    rage
    0.06
     crusher
    0.06
    Act Density 0.005%

    No Known Activations