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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Country
    -0.07
    CEEDED
    -0.07
    [file
    -0.07
     Dollars
    -0.07
    色泽
    -0.06
    APPED
    -0.06
    _dataset
    -0.06
    之情
    -0.06
     hol
    -0.06
     Database
    -0.06
    POSITIVE LOGITS
    ⌥
    0.07
    ren
    0.07
    ĥ
    0.07
    授予
    0.07
     abusing
    0.07
    มอบ
    0.06
    煴
    0.06
    ritch
    0.06
    %^
    0.06
    温柔
    0.06
    Act Density 0.065%

    No Known Activations