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

    Neuronpedia

    INDEX
    Explanations

    various languages and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Й
    0.50
    У
    0.45
    𝗦
    0.44
    īng
    0.44
     beberapa
    0.43
    К
    0.43
    Х
    0.43
    Ю
    0.42
    Ад
    0.42
     Fast
    0.41
    POSITIVE LOGITS
    UMBIA
    0.51
    jà
    0.50
    tocol
    0.44
    ্ষিক
    0.44
    肢
    0.44
    immä
    0.43
     அற
    0.42
     intermédiaire
    0.41
    とにかく
    0.40
     collateral
    0.40
    Act Density 0.004%

    No Known Activations