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

    Neuronpedia

    INDEX
    Explanations

    dates and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sajana
    0.38
     perí
    0.37
     கேள்
    0.36
     prosedur
    0.35
     vzděl
    0.35
     hazırl
    0.35
     fokus
    0.35
     procédure
    0.34
     wyk
    0.34
     društ
    0.33
    POSITIVE LOGITS
    л
    0.43
    ing
    0.40
    inna
    0.37
    ي
    0.37
    ic
    0.37
    ata
    0.36
    ل
    0.36
    it
    0.35
    ة
    0.34
    ት
    0.34
    Act Density 0.000%

    No Known Activations