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

    Neuronpedia

    INDEX
    Explanations

    hy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    城镇
    -0.07
    无锡
    -0.07
    官兵
    -0.07
    inton
    -0.07
     북
    -0.07
    图纸
    -0.06
    上述
    -0.06
     spoken
    -0.06
    ✱
    -0.06
     cottage
    -0.06
    POSITIVE LOGITS
     culture
    0.08
     hy
    0.08
     sanitized
    0.07
    欧元
    0.07
     Genius
    0.07
     hyperlink
    0.07
    ulously
    0.07
    jà
    0.07
    相当于
    0.07
     emphasis
    0.07
    Act Density 0.025%

    No Known Activations