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

    Neuronpedia

    INDEX
    Explanations

    competitive performance and traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nt
    0.51
    ley
    0.49
    +
    0.48
    nete
    0.48
    in
    0.47
    ale
    0.46
    EG
    0.45
    aron
    0.45
    ALL
    0.45
     strani
    0.45
    POSITIVE LOGITS
     Ouvrard
    0.51
    ताच
    0.50
    inairement
    0.49
    เท่า
    0.49
    მასრულ
    0.46
    надцати
    0.46
    人之
    0.45
    රි
    0.44
    біць
    0.44
    𝓭
    0.44
    Act Density 0.000%

    No Known Activations