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

    Neuronpedia

    INDEX
    Explanations

    numbers after calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     restantes
    0.48
    ла
    0.46
    लेषण
    0.45
     incidences
    0.45
    Mode
    0.45
    בית
    0.44
    ResBuffer
    0.43
    Му
    0.43
    Doch
    0.43
    Мо
    0.43
    POSITIVE LOGITS
     CNC
    0.48
     immortal
    0.47
     Nana
    0.46
     ۱۴
    0.46
     BFF
    0.45
     लगभग
    0.44
    nan
    0.44
     CRA
    0.44
     NaN
    0.44
     RAI
    0.44
    Act Density 0.031%

    No Known Activations