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

    Neuronpedia

    INDEX
    Explanations

    mask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ام
    0.76
    د
    0.74
    iem
    0.71
     is
    0.71
    er
    0.70
    i
    0.68
    >
    0.66
    is
    0.64
    amag
    0.64
    ال
    0.63
    POSITIVE LOGITS
     mask
    0.71
     মুখো
    0.68
     Masks
    0.66
    ם
    0.65
     I
    0.63
    Mask
    0.62
     Barrie
    0.62
     Spiele
    0.62
     masks
    0.61
     Mask
    0.60
    Act Density 0.002%

    No Known Activations