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

    Neuronpedia

    INDEX
    Explanations

    end-to-end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     To
    0.46
    sto
    0.39
     sto
    0.38
    ","/
    0.38
     goTo
    0.38
    decompose
    0.38
    selves
    0.37
    ঞ্ছ
    0.37
     scom
    0.37
    goTo
    0.35
    POSITIVE LOGITS
    々
    0.41
    对
    0.41
    対
    0.40
    對
    0.39
     Andrea
    0.38
     Var
    0.36
    Wire
    0.35
     Carol
    0.35
    Andrea
    0.35
    нах
    0.35
    Act Density 0.015%

    No Known Activations