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

    Neuronpedia

    INDEX
    Explanations

    Elara, Li, Erfanian, Kaelen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.30
     buddhav
    0.29
     Because
    0.27
     Phrases
    0.27
     SeekBar
    0.26
     I
    0.25
     drunkenness
    0.25
     Painters
    0.25
     Gingerbread
    0.24
     bulletins
    0.24
    POSITIVE LOGITS
    ও
    0.37
    ۵
    0.33
     in
    0.33
    ین
    0.32
    ın
    0.31
    og
    0.30
    سی
    0.30
    도
    0.30
    ای
    0.29
    ۶
    0.29
    Act Density 0.069%

    No Known Activations