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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зья
    0.39
     Critique
    0.37
    (!)
    0.35
     마련
    0.34
    ЕНИ
    0.34
     Wettbewer
    0.34
     Akademii
    0.33
     (!)
    0.33
     Roundtable
    0.33
     Beratung
    0.32
    POSITIVE LOGITS
    any
    0.41
    th
    0.39
    k
    0.37
    I
    0.36
    as
    0.35
    n
    0.35
     I
    0.35
    is
    0.35
    an
    0.34
    if
    0.34
    Act Density 0.018%

    No Known Activations