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

    Neuronpedia

    INDEX
    Explanations

    please share

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rah
    1.20
    ciences
    1.19
     capital
    1.15
    ian
    1.13
    ه‌
    1.11
     transit
    1.07
    ymmetry
    1.07
     duct
    1.06
    новых
    1.05
    yan
    1.04
    POSITIVE LOGITS
    followfollow
    1.54
    果た
    1.51
     Führung
    1.44
     Vorsitz
    1.42
    ഔ
    1.41
     završ
    1.38
    DONT
    1.37
     MAINT
    1.36
     dajj
    1.36
    मताओं
    1.36
    Act Density 0.000%

    No Known Activations