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

    Neuronpedia

    INDEX
    Explanations

    creators and recycled security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.52
    N
    0.49
    בי
    0.47
    開
    0.46
    Community
    0.46
    印度
    0.45
    美國
    0.45
    給大家
    0.45
    тить
    0.44
    מו
    0.44
    POSITIVE LOGITS
    goal
    0.52
    idz
    0.51
    lceil
    0.50
    n
    0.47
    potion
    0.46
    cG
    0.46
    string
    0.46
    dec
    0.45
    getCell
    0.45
    uses
    0.45
    Act Density 0.004%

    No Known Activations