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

    Neuronpedia

    INDEX
    Explanations

    ongoing actions and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ના
    0.54
    ের
    0.47
    更に
    0.45
    و
    0.43
    д
    0.43
    ८
    0.42
    っており
    0.41
    alten
    0.41
    나
    0.41
    ره
    0.41
    POSITIVE LOGITS
     a
    0.67
    ing
    0.65
    a
    0.65
    ة
    0.63
    -
    0.59
    il
    0.57
    ton
    0.55
    h
    0.54
    ine
    0.51
     at
    0.48
    Act Density 0.882%

    No Known Activations