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

    Neuronpedia

    INDEX
    Explanations

    reading files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tug
    0.39
    漳
    0.39
     esque
    0.38
     chirp
    0.38
     kontrast
    0.38
    iroz
    0.38
     slings
    0.38
     coef
    0.37
     cheerio
    0.37
     diagrama
    0.36
    POSITIVE LOGITS
     oğ
    0.40
    ادل
    0.38
     হান
    0.37
    हां
    0.36
    äm
    0.36
    м
    0.36
     encountered
    0.35
     Encounter
    0.35
    atypes
    0.35
    ற்ப
    0.35
    Act Density 0.000%

    No Known Activations