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
    诅
    -0.07
    쯕
    -0.07
    (URL
    -0.07
    ᨁ
    -0.07
    嗖
    -0.07
    מכבי
    -0.07
    ㅊ
    -0.07
     Gloves
    -0.06
     לבד
    -0.06
    .PL
    -0.06
    POSITIVE LOGITS
     Excellence
    0.08
     refin
    0.07
    和技术
    0.07
     Helsinki
    0.07
    seud
    0.07
    Standard
    0.07
    rial
    0.07
    jeta
    0.06
    int
    0.06
    vn
    0.06
    Act Density 0.014%

    No Known Activations