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

    Neuronpedia

    INDEX
    Explanations

    website comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'H
    -0.07
    องท
    -0.06
    rng
    -0.06
    021
    -0.06
    _ov
    -0.06
    _constant
    -0.06
    006
    -0.06
     scattering
    -0.06
    	where
    -0.06
    aton
    -0.06
    POSITIVE LOGITS
    ）。↵↵
    0.07
    .Override
    0.07
     ￣
    0.07
     tomu
    0.07
    ']]],↵
    0.07
     máte
    0.07
    elopment
    0.07
    _qs
    0.07
    。',↵
    0.06
    無し
    0.06
    Act Density 0.093%

    No Known Activations