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

    Neuronpedia

    INDEX
    Explanations

    control over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.03
    ke
    0.70
    ्स
    0.69
    d
    0.69
    ਆਂ
    0.64
    сь
    0.61
    ls
    0.61
    oeuvre
    0.60
    ${
    0.60
    Рис
    0.60
    POSITIVE LOGITS
     وعلى
    0.73
    ções
    0.71
    ار
    0.66
     самого
    0.66
    了一个
    0.65
     saldo
    0.64
     کرنے
    0.63
     início
    0.63
     لع
    0.63
    лкой
    0.62
    Act Density 0.377%

    No Known Activations