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

    Neuronpedia

    INDEX
    Explanations

    syntax elements commonly used in programming and markup languages

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

    Code snippets and special characters

    np_acts-logits-general · gemini-2.0-flash

    code syntax and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.59
    <bos>
    -0.55
    XmlAccessorType
    -0.51
    цезда
    -0.51
    SourceChecksum
    -0.51
     mergeFrom
    -0.49
    بالإنجليزية
    -0.49
    لاقات
    -0.47
    UrlResolution
    -0.45
    ][/
    -0.45
    POSITIVE LOGITS
    0.86
     synthase
    0.79
     noDo
    0.77
     AspNetCore
    0.77
    Hentet
    0.74
     pleaſure
    0.70
    Дереккөздер
    0.68
     cauſe
    0.62
     <<<<<<<<<<<<<<
    0.62
     uncomment
    0.59
    Act Density 0.203%

    No Known Activations