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
    1
    0.93
    การ
    0.90
     Không
    0.82
    9
    0.82
    ཋ
    0.82
    ко
    0.81
    мо
    0.79
    2
    0.78
     ซ
    0.76
    5
    0.74
    POSITIVE LOGITS
    しまう
    0.81
     lomb
    0.73
     ones
    0.72
     launchers
    0.70
     toppings
    0.70
     sepanjang
    0.70
     которыми
    0.70
     duk
    0.69
     starters
    0.69
     olduk
    0.68
    Act Density 0.127%

    No Known Activations