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

    Neuronpedia

    INDEX
    Explanations

    V

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jak
    -0.07
    utory
    -0.06
    inth
    -0.06
     wel
    -0.06
    ehicle
    -0.06
    ISIBLE
    -0.06
    cal
    -0.06
     symb
    -0.06
     rám
    -0.06
     Ook
    -0.06
    POSITIVE LOGITS
     τέ
    0.08
     možné
    0.07
    vý
    0.07
    _CHO
    0.07
    .middleware
    0.06
    ٔ
    0.06
    (album
    0.06
    ние
    0.06
    ORG
    0.06
    .ak
    0.06
    Act Density 0.005%

    No Known Activations