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

    Neuronpedia

    INDEX
    Explanations

    physical requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abc
    0.41
     lepiej
    0.39
     reverting
    0.39
     ":"
    0.39
    远
    0.38
    ably
    0.38
     حقوق
    0.37
    chang
    0.37
     Statistical
    0.36
    遁
    0.36
    POSITIVE LOGITS
     confe
    0.42
    тивным
    0.41
     competitiveness
    0.39
    चि
    0.39
     treo
    0.39
    ioides
    0.39
    壟
    0.37
     scratch
    0.37
    assertion
    0.35
     Spit
    0.35
    Act Density 0.000%

    No Known Activations