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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming functions, error handling, and potentially harmful actions

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

    morphological characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vereinigung
    -0.43
    ep
    -0.40
    io
    -0.39
    ew
    -0.39
    ey
    -0.39
     Associação
    -0.39
    öpfer
    -0.38
     manio
    -0.38
    py
    -0.38
    iew
    -0.37
    POSITIVE LOGITS
    /**
    1.18
    BagConstraints
    0.96
    Gigi
    0.80
     getLast
    0.79
    niająca
    0.76
    getLast
    0.75
    ="{{$
    0.73
     Gigi
    0.71
     getIs
    0.69
     BigInt
    0.65
    Act Density 0.008%

    No Known Activations