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

    Neuronpedia

    INDEX
    Explanations

    decisions related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Title
    0.72
    FilePath
    0.71
     ಮತ್ತು
    0.69
     എന്നാല്‍
    0.67
     Ն
    0.66
    भग
    0.66
    Recipe
    0.65
    Cherry
    0.65
     අව
    0.64
    災害
    0.63
    POSITIVE LOGITS
     рели
    0.70
     brackets
    0.68
     lohnt
    0.67
     assistance
    0.67
    ভাষ
    0.66
     insertions
    0.66
     bracket
    0.66
     sensitized
    0.65
     compt
    0.65
     kuul
    0.65
    Act Density 0.004%

    No Known Activations