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

    Neuronpedia

    INDEX
    Explanations

    you to create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েও
    1.23
    lari
    1.13
    ுங்கள்
    1.10
    ются
    1.08
    ح
    1.07
    yh
    1.07
    टिक
    1.06
    t
    1.05
    цията
    1.05
     Hud
    1.04
    POSITIVE LOGITS
    et
    1.12
     desto
    1.07
    '}}
    1.07
    ‌ای
    1.03
    popular
    1.02
     azimuthal
    1.02
    
    0.99
    मुझे
    0.99
     mani
    0.99
     म्यूचुअल
    0.98
    Act Density 0.005%

    No Known Activations