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

    Neuronpedia

    INDEX
    Explanations

    before or pre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    පි
    0.46
     ט
    0.44
     jsou
    0.44
    深圳市
    0.44
    卒業
    0.42
     seguimiento
    0.41
     serii
    0.41
     خ
    0.40
     stopni
    0.40
     ස
    0.40
    POSITIVE LOGITS
    ам
    0.45
     instead
    0.45
     बजाय
    0.45
    ¹,
    0.45
    **,
    0.44
    unshift
    0.44
    instead
    0.44
     antecedent
    0.43
    prepend
    0.41
     или
    0.40
    Act Density 0.004%

    No Known Activations