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

    Neuronpedia

    INDEX
    Explanations

    for word or variable name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arasındaki
    0.41
     recirculation
    0.40
     πολλ
    0.40
    :
    0.40
    lanır
    0.39
     mange
    0.39
    ूक
    0.38
     eril
    0.38
    结尾
    0.38
    $:
    0.37
    POSITIVE LOGITS
     ৩৪
    0.42
    }
    0.41
    ")
    0.39
    andidates
    0.39
    ionista
    0.39
    શ્મી
    0.39
     inizio
    0.38
    ölf
    0.38
     ক্রিকেটার
    0.38
    ეგ
    0.38
    Act Density 0.021%

    No Known Activations