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

    Neuronpedia

    INDEX
    Explanations

    Convert plans and ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    젹
    0.45
    णु
    0.41
     gi
    0.40
    <0xB6>
    0.40
    ',)
    0.39
    ኳ
    0.39
     ملازمت
    0.38
    諱
    0.38
    най
    0.38
    ой
    0.38
    POSITIVE LOGITS
     Convert
    0.47
     existing
    0.42
     Convertible
    0.41
     current
    0.40
     preset
    0.40
    preset
    0.40
     Konzept
    0.40
     beste
    0.40
    current
    0.39
     Autom
    0.39
    Act Density 0.002%

    No Known Activations