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

    Neuronpedia

    INDEX
    Explanations

    classifications and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    טו
    0.36
    Despatx
    0.35
    రా
    0.32
     бассе
    0.32
    𒊑
    0.32
    НА
    0.32
     వాహ
    0.32
    미
    0.32
    ер
    0.32
    HYDRO
    0.32
    POSITIVE LOGITS
    .
    0.35
     (
    0.33
    ↵
    0.33
     classification
    0.30
    ,
    0.30
    0.28
     word
    0.28
    -
    0.28
     banner
    0.27
     help
    0.27
    Act Density 0.593%

    No Known Activations