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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     refining
    -0.06
     تفاوت
    -0.06
    ducible
    -0.06
     él
    -0.06
    ventario
    -0.06
     مرات
    -0.06
    об
    -0.06
    intColor
    -0.06
    (avg
    -0.06
     Zhang
    -0.06
    POSITIVE LOGITS
    oq
    0.07
    .slider
    0.07
    นา
    0.06
    ็กซ
    0.06
    _od
    0.06
    _SELECT
    0.06
    _expression
    0.06
    .
↵
    0.06
     soup
    0.06
    _INPUT
    0.06
    Act Density 0.002%

    No Known Activations