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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emitted
    -0.08
    تد
    -0.08
     일을
    -0.07
    贞
    -0.07
    ‥
    -0.07
    센
    -0.07
    สมาช
    -0.07
    -producing
    -0.07
     علين
    -0.07
     breathed
    -0.07
    POSITIVE LOGITS
     curvature
    0.08
    刹车
    0.07
    响应
    0.07
    Background
    0.07
    假设
    0.07
     BU
    0.07
     unexpected
    0.07
     NCAA
    0.06
    bio
    0.06
     Marketing
    0.06
    Act Density 0.073%

    No Known Activations