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

    Neuronpedia

    INDEX
    Explanations

    some followed by varied items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.60
    standard
    0.57
     Potomac
    0.57
    もら
    0.54
     kebanyakan
    0.52
    O
    0.52
    太郎
    0.51
     větš
    0.51
    Jordan
    0.50
    f
    0.50
    POSITIVE LOGITS
    л
    0.64
     as
    0.63
     on
    0.58
     degree
    0.57
     or
    0.56
     выпла
    0.52
    ル
    0.51
     результате
    0.50
    ल
    0.50
    ס
    0.50
    Act Density 0.068%

    No Known Activations