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

    Neuronpedia

    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atta
    -0.07
     Dict
    -0.07
     客
    -0.07
     तत
    -0.06
    喝
    -0.06
     ठ
    -0.06
    _the
    -0.06
     тебе
    -0.06
     sprites
    -0.06
     futile
    -0.06
    POSITIVE LOGITS
     REGISTER
    0.07
    devil
    0.06
    alie
    0.06
    _locator
    0.06
     isc
    0.06
    'nın
    0.06
    Wie
    0.06
    omatic
    0.06
     enforcing
    0.06
    -sector
    0.06
    Act Density 0.045%

    No Known Activations