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

    Neuronpedia

    INDEX
    Explanations

    snails and snail actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.04
    '
    1.02
    ะ
    1.00
    (
    0.92
    0
    0.88
    ের
    0.80
    ні
    0.79
    स
    0.78
    ých
    0.77
    ים
    0.77
    POSITIVE LOGITS
     coloc
    0.78
     toa
    0.74
     snails
    0.73
     snail
    0.73
     இருக்கும்
    0.72
     allé
    0.72
     don
    0.71
     do
    0.71
    蜗
    0.69
    وضع
    0.69
    Act Density 0.003%

    No Known Activations