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

    Neuronpedia

    INDEX
    Explanations

    Ces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FOUND
    -0.07
    产出
    -0.07
     zien
    -0.07
    IPv
    -0.07
    Kevin
    -0.07
     Morr
    -0.06
    menuItem
    -0.06
    -equipped
    -0.06
    澴
    -0.06
    שפ
    -0.06
    POSITIVE LOGITS
     relaxation
    0.08
    orelease
    0.07
     steady
    0.07
     emergence
    0.07
    国企
    0.07
     jewels
    0.07
     działania
    0.07
     réserve
    0.07
    共
    0.07
     tossed
    0.06
    Act Density 0.037%

    No Known Activations