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

    Neuronpedia

    INDEX
    Explanations

    documenting lives and histories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.72
     by
    0.64
     (
    0.63
    et
    0.62
    ed
    0.61
    oe
    0.60
    of
    0.59
    je
    0.58
    ная
    0.57
    db
    0.57
    POSITIVE LOGITS
     embold
    0.54
    מ
    0.52
     splendour
    0.51
     enquire
    0.51
    \},
    0.50
    ENSITY
    0.50
     erro
    0.49
     Ethel
    0.49
    瑉
    0.49
     forums
    0.49
    Act Density 0.003%

    No Known Activations