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

    Neuronpedia

    INDEX
    Explanations

    with respect or sensitivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     می‌تواند
    0.36
    బడి
    0.35
    SUN
    0.35
     Sunil
    0.35
     Chlor
    0.34
     క్ష
    0.34
    額
    0.33
     covariate
    0.33
     ഇട
    0.33
    Weak
    0.33
    POSITIVE LOGITS
     coisa
    0.48
     understatement
    0.46
    things
    0.46
     sabi
    0.43
     things
    0.42
    ޗ
    0.42
    thing
    0.42
     விஷய
    0.41
    ྂ
    0.41
    fY
    0.41
    Act Density 0.000%

    No Known Activations