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

    Neuronpedia

    INDEX
    Explanations

    relations and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    سكر
    0.39
     طويل
    0.38
     leichter
    0.36
    كة
    0.35
    '`,
    0.35
    خة
    0.35
    ска
    0.34
    覆
    0.34
    يمة
    0.34
     ভর্তি
    0.34
    POSITIVE LOGITS
    จะ
    0.49
     incest
    0.47
    ust
    0.46
    isations
    0.46
     Несмотря
    0.45
    ด
    0.45
     この
    0.45
    urricular
    0.44
     सद्
    0.44
     dissonance
    0.44
    Act Density 0.000%

    No Known Activations