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

    Neuronpedia

    INDEX
    Explanations

    some basic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vivido
    1.53
    ा
    1.34
    iary
    1.27
    ᴀ
    1.27
    ই
    1.26
    써
    1.22
    dominated
    1.21
    ipped
    1.20
    textit
    1.20
    ність
    1.20
    POSITIVE LOGITS
    ب
    2.47
     semblance
    1.85
    ones
    1.60
    on
    1.60
     få
    1.52
    maßen
    1.52
     wenige
    1.51
     leeway
    1.49
    how
    1.48
    러
    1.43
    Act Density 0.188%

    No Known Activations