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

    Neuronpedia

    INDEX
    Explanations

    mutable variable declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     víctima
    0.89
     to
    0.79
     culto
    0.77
    У
    0.76
    一些
    0.73
    ן
    0.73
    "।
    0.71
    ಕಾಶ
    0.71
    І
    0.70
    ი
    0.70
    POSITIVE LOGITS
    s
    0.71
     g
    0.58
    ou
    0.57
     sConfig
    0.57
     ఉండ
    0.57
    గ
    0.57
    nahmen
    0.56
     ursprüng
    0.56
     hati
    0.56
    ra
    0.55
    Act Density 0.005%

    No Known Activations