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

    Neuronpedia

    INDEX
    Explanations

    500

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ild
    -0.07
     Unt
    -0.06
     Registration
    -0.06
    _player
    -0.06
     decoding
    -0.06
    Kal
    -0.06
     setTitle
    -0.06
    ervlet
    -0.06
    Story
    -0.06
     Winter
    -0.06
    POSITIVE LOGITS
    500
    0.09
    537
    0.07
    950
    0.07
    300
    0.07
    550
    0.07
    299
    0.07
    aussian
    0.07
    105
    0.06
     divis
    0.06
    974
    0.06
    Act Density 0.001%

    No Known Activations