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

    Neuronpedia

    INDEX
    Explanations

    sentences that convey a sense of confusion or absurdity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    documentation / .

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diwedd
    -0.57
    исленность
    -0.56
     defaultstate
    -0.56
    LabelTagHelper
    -0.52
    saraba
    -0.50
    expandindo
    -0.50
    bootstrapcdn
    -0.50
    InputTagHelper
    -0.49
    Tikang
    -0.48
    SharedDtor
    -0.48
    POSITIVE LOGITS
     AssemblyProduct
    0.36
    tellung
    0.36
    hado
    0.35
     Biôgrafia
    0.35
    hagy
    0.34
    sleeping
    0.34
    ณ์
    0.33
     dormir
    0.32
     diversión
    0.32
     AssemblyCompany
    0.32
    Act Density 0.111%

    No Known Activations