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

    Neuronpedia

    INDEX
    Explanations

    (Around price range)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pe
    0.64
    te
    0.64
    se
    0.64
    ist
    0.63
    ta
    0.63
    ve
    0.61
    j
    0.54
    ze
    0.53
    cs
    0.53
    ed
    0.52
    POSITIVE LOGITS
    ựng
    0.62
     каждый
    0.59
     эти
    0.57
     reduz
    0.55
     человеком
    0.55
     одной
    0.54
     dihap
    0.54
     ekki
    0.54
    REGIUNE
    0.54
     детьми
    0.54
    Act Density 3.806%

    No Known Activations