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

    Neuronpedia

    INDEX
    Explanations

    switch

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    结局
    0.68
    钵
    0.64
    লেট
    0.62
     macrophages
    0.61
    leti
    0.59
    缽
    0.59
    شهاد
    0.59
     متحده
    0.59
     TERR
    0.58
    abst
    0.57
    POSITIVE LOGITS
    blade
    0.88
    yard
    0.83
    gear
    0.77
    ero
    0.75
    board
    0.73
    boards
    0.70
    backs
    0.70
    yards
    0.67
    ERO
    0.67
    grass
    0.66
    Act Density 0.009%

    No Known Activations