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

    Neuronpedia

    INDEX
    Explanations

    &P

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    руш
    -0.07
     Sunset
    -0.07
    �
    -0.07
    門
    -0.06
     boarding
    -0.06
     Jana
    -0.06
    Bounds
    -0.06
    corp
    -0.06
    είς
    -0.06
    Mad
    -0.06
    POSITIVE LOGITS
     professors
    0.07
     ".$
    0.07
    .history
    0.06
     т
    0.06
     grayscale
    0.06
    ,output
    0.06
    -toggler
    0.06
    <path
    0.06
     experiment
    0.06
    _ABI
    0.06
    Act Density 0.015%

    No Known Activations