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

    Neuronpedia

    INDEX
    Explanations

    will not fulfill request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    珺
    0.39
    راع
    0.38
    städter
    0.37
    ]=\
    0.37
    èdes
    0.37
    >=</
    0.36
    حدد
    0.36
    ávají
    0.36
    enswert
    0.36
     Beginn
    0.35
    POSITIVE LOGITS
     चें
    0.45
     puso
    0.41
    nö
    0.41
    がい
    0.41
    টি
    0.40
    र्‍या
    0.39
    सि
    0.39
    Pins
    0.38
     مبنی
    0.37
     sufrido
    0.37
    Act Density 0.075%

    No Known Activations