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

    Neuronpedia

    INDEX
    Explanations

    possessive plurals and 'fit'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ḍ
    0.46
     вас
    0.41
     iā
    0.40
    IPT
    0.40
     cadeira
    0.39
    కంగా
    0.38
     thận
    0.38
     Prediction
    0.38
     SS
    0.38
     Prepaid
    0.38
    POSITIVE LOGITS
     Leur
    0.44
    their
    0.44
    Their
    0.40
    如有
    0.40
     their
    0.40
     quarrel
    0.40
     അവരുടെ
    0.40
     loro
    0.39
    wny
    0.39
     leur
    0.39
    Act Density 0.000%

    No Known Activations