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

    Neuronpedia

    INDEX
    Explanations

    .gov domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সভাপতিত্ব
    0.42
    劲
    0.41
    锺
    0.41
     reign
    0.38
    找不到
    0.38
     regener
    0.38
     footballer
    0.37
     tends
    0.37
     xúc
    0.37
     neat
    0.37
    POSITIVE LOGITS
    each
    0.38
    сім
    0.38
    mbox
    0.35
     Sync
    0.35
     راست
    0.35
     صنعت
    0.35
     लोक
    0.35
    PerTrial
    0.34
    Heights
    0.34
    shut
    0.34
    Act Density 0.045%

    No Known Activations