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

    Neuronpedia

    INDEX
    Explanations

    Han Solo and smuggler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    0.83
    지
    0.80
    W
    0.80
    يز
    0.78
    기
    0.75
    g
    0.74
    M
    0.72
    t
    0.71
    Қ
    0.70
    D
    0.69
    POSITIVE LOGITS
     мень
    0.59
    ästä
    0.59
    \
    0.57
     contacter
    0.57
    🏻
    0.56
     bantuan
    0.55
     роках
    0.55
     verden
    0.55
     बचने
    0.55
     rattling
    0.54
    Act Density 0.004%

    No Known Activations