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

    Neuronpedia

    INDEX
    Explanations

    wave properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /common
    -0.07
    椆
    -0.07
    ATIONAL
    -0.07
     הישראלי
    -0.07
     conspic
    -0.06
    empt
    -0.06
    三角
    -0.06
    Ⱡ
    -0.06
    长时间
    -0.06
    OfFile
    -0.06
    POSITIVE LOGITS
    حوال
    0.08
     propia
    0.07
    กาย
    0.07
     través
    0.06
    اف
    0.06
    PW
    0.06
     flame
    0.06
     Bab
    0.06
     homem
    0.06
    irting
    0.06
    Act Density 0.013%

    No Known Activations