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

    Neuronpedia

    INDEX
    Explanations

    `)`

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jul
    -0.08
    lays
    -0.07
     BACKGROUND
    -0.07
     ціл
    -0.07
    'elle
    -0.07
    xx
    -0.07
    363
    -0.07
     MULT
    -0.07
    optimizer
    -0.07
    763
    -0.06
    POSITIVE LOGITS
    吸
    0.06
    mış
    0.06
    getParent
    0.06
     mám
    0.06
     guarda
    0.06
    contest
    0.06
    	Item
    0.06
     deity
    0.06
    нова
    0.06
    (length
    0.06
    Act Density 0.004%

    No Known Activations