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

    Neuronpedia

    INDEX
    Explanations

    numbers after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     וה
    0.81
     spitting
    0.78
    elly
    0.77
    ret
    0.75
     desirable
    0.74
    税込
    0.74
     मुताबिक
    0.73
     इसलिये
    0.73
     moisture
    0.72
     zcela
    0.72
    POSITIVE LOGITS
     Dank
    1.02
     трав
    1.01
     Enfer
    0.99
     шер
    0.96
    Potion
    0.96
     Lob
    0.95
     Yas
    0.94
    碘
    0.93
     використову
    0.93
    धे
    0.92
    Act Density 0.080%

    No Known Activations