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

    Neuronpedia

    INDEX
    Explanations

    lists and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ご覧
    0.38
     досить
    0.37
     واله
    0.36
    ᅩ
    0.35
    ‍♂️
    0.35
    𝐋
    0.34
    📍
    0.33
    𝐑
    0.33
     लो
    0.32
    Desde
    0.32
    POSITIVE LOGITS
    !!!!!!!!!!!!!!!!
    0.43
     యొక్క
    0.41
     decreases
    0.40
     thereby
    0.39
    从而
    0.39
     deleterious
    0.37
     wirelessly
    0.37
    !!!!!!!!
    0.35
     nonnegative
    0.35
     hypothesized
    0.35
    Act Density 0.004%

    No Known Activations