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

    Neuronpedia

    INDEX
    Explanations

    list item separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vina
    0.39
    redientes
    0.37
     Odinga
    0.37
    amano
    0.37
    asse
    0.36
     vistazo
    0.36
    arz
    0.36
    ána
    0.36
    rito
    0.36
     procedente
    0.36
    POSITIVE LOGITS
     création
    0.39
     สร้าง
    0.38
     creation
    0.38
    Creating
    0.38
    สร้าง
    0.37
    CrossRef
    0.37
     пі
    0.37
     പഠ
    0.37
     całym
    0.37
    HT
    0.37
    Act Density 0.001%

    No Known Activations