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

    Neuronpedia

    INDEX
    Explanations

    start of command or section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    啷
    0.54
     on
    0.54
     ndani
    0.51
     thỏa
    0.50
    0
    0.50
     çıkart
    0.50
     bardziej
    0.49
     nope
    0.48
    د
    0.48
    ד
    0.48
    POSITIVE LOGITS
    на
    0.66
     I
    0.55
    OR
    0.52
    वात
    0.50
     спри
    0.49
    ures
    0.49
    ਰ
    0.48
     जीने
    0.48
    ಾರಂಭ
    0.47
     مراسم
    0.46
    Act Density 0.041%

    No Known Activations