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

    Neuronpedia

    INDEX
    Explanations

    search and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.45
    4
    0.44
     imposes
    0.42
     embeds
    0.40
     declaraciones
    0.40
    N
    0.39
    iefert
    0.38
     conduits
    0.38
    0
    0.38
     delivers
    0.38
    POSITIVE LOGITS
    lı
    0.50
    uğu
    0.49
     ಹೀ
    0.49
     rồi
    0.48
     নিশ
    0.48
    ları
    0.47
    রিক
    0.46
     লী
    0.46
    rono
    0.46
    larını
    0.46
    Act Density 0.000%

    No Known Activations