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

    Neuronpedia

    INDEX
    Explanations

    Unit conversions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phú
    -0.07
    有待
    -0.07
     Katy
    -0.07
    典雅
    -0.07
    죔
    -0.07
    _REPLY
    -0.07
    Without
    -0.06
    簏
    -0.06
    Ƀ
    -0.06
    Volumes
    -0.06
    POSITIVE LOGITS
    )});↵
    0.07
     Overall
    0.06
     overlapping
    0.06
     tightening
    0.06
    ")↵↵↵
    0.06
    );↵↵↵
    0.06
    //
↵
    0.06
    ((*
    0.06
    _ER
    0.06
    护理
    0.06
    Act Density 0.004%

    No Known Activations