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

    Neuronpedia

    INDEX
    Explanations

    General Guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cakes
    1.08
    ant
    1.08
    ب
    1.08
    iro
    1.07
     els
    1.04
    nas
    1.04
    ativo
    1.02
    在外
    1.00
     pomer
    0.98
    ę
    0.97
    POSITIVE LOGITS
    ы
    1.40
    ित
    1.35
    я
    1.29
    ме
    1.22
    ؒ
    1.18
    𝙀
    1.16
    1.16
    ポリシー
    1.16
    requencies
    1.14
    ни
    1.14
    Act Density 0.001%

    No Known Activations