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

    Neuronpedia

    INDEX
    Explanations

    ological

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sends
    -0.08
    뷗
    -0.07
    +".
    -0.06
    伣
    -0.06
     adjusted
    -0.06
    _ENCODE
    -0.06
    Knight
    -0.06
    谲
    -0.06
    	initialize
    -0.06
    做得
    -0.06
    POSITIVE LOGITS
     moons
    0.07
    בלים
    0.07
    .white
    0.07
     kadar
    0.07
    おり
    0.07
    ogs
    0.07
     mediaPlayer
    0.07
    0.07
    тал
    0.07
    .v
    0.07
    Act Density 0.003%

    No Known Activations