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

    Neuronpedia

    INDEX
    Explanations

    numbers starting with 80

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    酽
    0.41
    ម្រ
    0.41
    اول
    0.39
    Usuarios
    0.39
    الح
    0.39
    PUBL
    0.39
    धिकारियों
    0.37
    Samb
    0.36
    स्परिक
    0.36
    ﺼ
    0.36
    POSITIVE LOGITS
    %
    0.56
     वर्षीय
    0.55
    년대
    0.52
     kDa
    0.50
    %+
    0.50
    kDa
    0.50
     percentile
    0.48
    th
    0.47
    percent
    0.47
     percent
    0.47
    Act Density 0.079%

    No Known Activations