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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     physique
    -0.07
    紧紧围绕
    -0.07
     vigorously
    -0.07
    quoise
    -0.07
     perf
    -0.07
     Nylon
    -0.06
    лиз
    -0.06
    ⛔
    -0.06
    렷
    -0.06
    _med
    -0.06
    POSITIVE LOGITS
    ថ
    0.07
    .='
    0.07
    triangle
    0.07
     ביח
    0.07
    .transition
    0.06
     (\<
    0.06
    畜
    0.06
     לרכ
    0.06
    �
    0.06
     FAC
    0.06
    Act Density 0.111%

    No Known Activations