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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    還元
    0.42
    pragma
    0.41
    manip
    0.41
     rhetoric
    0.41
    camouflage
    0.40
    டிக்க
    0.39
    ɟ
    0.38
    numerator
    0.38
    魯
    0.37
     বাহিনীকে
    0.36
    POSITIVE LOGITS
    シーズ
    0.48
     নির্
    0.38
     Leasing
    0.37
    šel
    0.37
     leasing
    0.36
     vợ
    0.36
     Skype
    0.36
    ారు
    0.36
     MTA
    0.36
     владель
    0.35
    Act Density 0.000%

    No Known Activations