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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and symbols

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

    injury represents Kyutama opportunity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fact
    -0.37
    feature
    -0.36
     atlet
    -0.34
     lupa
    -0.33
    XtraReports
    -0.32
     OkHttpClient
    -0.32
     yours
    -0.32
     athlete
    -0.31
     tuyo
    -0.31
     atleta
    -0.31
    POSITIVE LOGITS
    0.63
    ########.
    0.55
    лтемелер
    0.53
    OGND
    0.51
     propOrder
    0.50
    ronpa
    0.50
    ViewImports
    0.49
     ddelweddau
    0.47
     يتيمه
    0.47
    principalColumn
    0.47
    Act Density 0.257%

    No Known Activations