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

    Neuronpedia

    INDEX
    Explanations

    Programming bugs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     speakers
    -0.07
    Parms
    -0.07
    getParameter
    -0.07
    ioctl
    -0.07
     guarante
    -0.07
    Brush
    -0.06
    Claims
    -0.06
    navbarDropdown
    -0.06
    高水平
    -0.06
    encion
    -0.06
    POSITIVE LOGITS
    ぺ
    0.07
    球星
    0.07
     ace
    0.06
    印花
    0.06
     guts
    0.06
    跟进
    0.06
    ód
    0.06
    歲
    0.06
     após
    0.06
    🖤
    0.06
    Act Density 0.092%

    No Known Activations