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

    Neuronpedia

    INDEX
    Explanations

    app service http models dto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ------------
    0.50
    ).
    0.50
     Mỗi
    0.46
    )-$
    0.46
    )--
    0.46
    {})
    0.45
    )‏
    0.45
     Кла
    0.43
     Και
    0.43
     따라서
    0.43
    POSITIVE LOGITS
    as
    0.73
    ם
    0.60
    ¹
    0.58
     as
    0.58
     a
    0.52
    tach
    0.52
    та
    0.51
    EMENT
    0.51
    こちら
    0.51
     práci
    0.50
    Act Density 0.000%

    No Known Activations