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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and punctuation in a programming context

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

    Code or markup snippets ending in specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    By aluminum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.84
     ujednoznacz
    -0.79
     يتيمه
    -0.77
     JAXB
    -0.72
    RectangleBorder
    -0.67
    parsedMessage
    -0.62
    mány
    -0.60
     estekak
    -0.60
    Encyklopedia
    -0.60
     שוליים
    -0.58
    POSITIVE LOGITS
     the
    0.57
    +#+#
    0.57
    BorderFactory
    0.55
     The
    0.53
    Eksteraj
    0.53
     мәкал
    0.51
    탤
    0.49
     viewDidLoad
    0.48
     dAtA
    0.48
     layui
    0.46
    Act Density 0.091%

    No Known Activations