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

    Neuronpedia

    INDEX
    Explanations

    Game effects/damage description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CCP
    -0.06
    	git
    -0.06
    _reserved
    -0.06
     Anthem
    -0.06
    employ
    -0.06
     predecessors
    -0.06
    orna
    -0.06
    洋
    -0.06
    ullivan
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    SUR
    0.06
    NotEmpty
    0.06
     Wins
    0.06
     outra
    0.06
     Outdoor
    0.06
     출연
    0.06
     exclude
    0.06
     Гол
    0.06
     서로
    0.06
    classify
    0.06
    Act Density 0.018%

    No Known Activations