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

    Neuronpedia

    INDEX
    Explanations

    environmentally responsible living

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eroy
    0.79
    Leet
    0.76
    S
    0.73
    as
    0.72
    르
    0.70
    upyter
    0.70
    Buenos
    0.69
    स्क
    0.68
    ing
    0.68
    ordinate
    0.67
    POSITIVE LOGITS
    vorschau
    1.00
    0.90
     speck
    0.84
    داف
    0.83
    éments
    0.81
    rapped
    0.81
    friendly
    0.80
     conserving
    0.79
     fopen
    0.79
     (\"
    0.79
    Act Density 0.250%

    No Known Activations