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

    Neuronpedia

    INDEX
    Explanations

    code include directives and related syntax in programming documents

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

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -1.05
     незавершена
    -1.02
    mtrl
    -0.97
    -0.96
     GenerationType
    -0.96
    ьаж
    -0.94
     AssemblyCulture
    -0.94
    IndentedString
    -0.91
    WebVitals
    -0.90
    HasAnnotation
    -0.87
    POSITIVE LOGITS
    ↵↵
    0.53
    ↵
    0.49
    <eos>
    0.48
    !
    0.47
    等
    0.46
    …
    0.45
    .
    0.43
    0.42
    ;
    0.42
    –
    0.42
    Act Density 0.066%
    No Known Activations