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

    Neuronpedia

    INDEX
    Explanations

    resist viruses and questions why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     besk
    0.49
     skut
    0.47
     Efficient
    0.46
    ться
    0.46
     एक्सप्रेस
    0.46
    ItemStack
    0.46
     τις
    0.45
    いく
    0.45
     mackerel
    0.44
     branchNode
    0.44
    POSITIVE LOGITS
    emaker
    0.48
    aidh
    0.47
    Prz
    0.46
    alez
    0.46
    стива
    0.45
    Arth
    0.45
    ➚
    0.45
    تي
    0.44
    AMENT
    0.44
    师傅
    0.44
    Act Density 0.000%

    No Known Activations