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

    Neuronpedia

    INDEX
    Explanations

    elements related to code syntax and structure in programming languages

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

    Code related to decoding or writing data

    np_acts-logits-general · gemini-2.0-flash

    `try` or `if` in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.81
    AnchorStyles
    -0.81
    SequentialGroup
    -0.77
     '\\;'
    -0.76
    StructEnd
    -0.69
     endwhile
    -0.69
    basicConfig
    -0.69
    IntoConstraints
    -0.68
    ativement
    -0.68
     nakalista
    -0.68
    POSITIVE LOGITS
    WriteLiteral
    0.49
    BeginContext
    0.48
    Autoritní
    0.43
     azar
    0.43
    zard
    0.42
    erweise
    0.41
     Corm
    0.40
    bumptech
    0.39
    Liet
    0.39
     confess
    0.38
    Act Density 0.004%

    No Known Activations