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

    Neuronpedia

    INDEX
    Explanations

    Here are a few, some, five

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     campuran
    0.74
     totalité
    0.71
    両
    0.68
     combine
    0.68
     दाह
    0.67
     மொத்த
    0.65
     podendo
    0.65
    ólogos
    0.64
     Million
    0.63
     entirety
    0.62
    POSITIVE LOGITS
     few
    1.11
     quelques
    0.96
     some
    0.95
     vài
    0.84
    some
    0.82
     qualche
    0.81
     Few
    0.81
    few
    0.80
     några
    0.80
     Quelques
    0.80
    Act Density 0.263%

    No Known Activations