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

    Neuronpedia

    INDEX
    Explanations

    Add bubbles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dụng
    1.32
    in
    1.08
    !\!\
    1.06
    سطس
    1.06
    man
    1.06
    spec
    1.04
     অবশ্য
    0.99
    inien
    0.98
    erà
    0.97
    ر
    0.97
    POSITIVE LOGITS
    ᠯ
    1.21
     retarded
    1.21
    Pedidos
    1.21
    gradients
    1.21
    程序的
    1.21
    carrot
    1.18
     ngok
    1.16
    ृता
    1.16
     repeal
    1.14
    㖑
    1.14
    Act Density 0.000%

    No Known Activations