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

    Neuronpedia

    INDEX
    Explanations

    uniformity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.54
    ühlt
    0.52
    VALUES
    0.52
    itiba
    0.52
    ENTA
    0.50
    QUA
    0.50
    Values
    0.50
     கிட
    0.49
    ispo
    0.48
    lipped
    0.48
    POSITIVE LOGITS
     daripada
    0.54
    نات
    0.52
    ป
    0.49
    ਪ
    0.49
    hatan
    0.49
     perdagangan
    0.49
     setor
    0.49
    т
    0.49
     seme
    0.48
    ส
    0.48
    Act Density 0.000%

    No Known Activations