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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     освіти
    -0.07
    【
    -0.07
     Lords
    -0.07
     東京
    -0.06
    _AL
    -0.06
     TEN
    -0.06
     及
    -0.06
    アイ
    -0.06
    рити
    -0.06
    啪
    -0.06
    POSITIVE LOGITS
    opolitan
    0.07
    '=>
    0.07
     McKin
    0.07
    found
    0.07
     Diameter
    0.06
    "x
    0.06
    ,”
    0.06
    ,'
    0.06
     �
    0.06
    _INS
    0.06
    Act Density 0.004%

    No Known Activations