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

    Neuronpedia

    INDEX
    Explanations

    code diffs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     эсеп
    0.45
     hypersur
    0.44
    ஜ்மஹால்
    0.43
    hton
    0.43
    လို့
    0.41
     mocy
    0.40
    orderDisplay
    0.40
     TouchUtils
    0.39
     Akhtar
    0.39
     tutaj
    0.39
    POSITIVE LOGITS
    廉
    0.42
    ，
    0.42
    some
    0.39
    subscription
    0.38
    nos
    0.37
    sus
    0.37
    ]+
    0.37
    一般
    0.36
    サ
    0.36
    弁当
    0.36
    Act Density 0.000%

    No Known Activations