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

    Neuronpedia

    INDEX
    Explanations

    break down and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addirittura
    0.43
     даже
    0.39
     sogar
    0.38
     болезни
    0.38
    emás
    0.38
     algún
    0.37
     ждать
    0.36
     Daarna
    0.35
     позже
    0.35
     পরেও
    0.35
    POSITIVE LOGITS
     zarówno
    0.46
     examines
    0.45
     gathers
    0.43
     This
    0.41
     sowohl
    0.41
     explores
    0.40
     με
    0.39
     combines
    0.39
    对于
    0.38
     finds
    0.38
    Act Density 0.857%

    No Known Activations