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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming and variable assignment contexts

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

    Code and symbols in Rust and Javascript

    np_acts-logits-general · gemini-2.0-flash

    connection is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CodeAnalysis
    -0.63
    publicain
    -0.52
    RunWith
    -0.51
    nestjs
    -0.49
    figur
    -0.49
     vertre
    -0.48
     IDisposable
    -0.47
     Ferner
    -0.47
    UnknownFieldSet
    -0.47
    (":");
    -0.46
    POSITIVE LOGITS
    match
    1.02
     match
    0.94
    Some
    0.74
     Some
    0.72
    if
    0.64
    format
    0.63
     if
    0.62
    Match
    0.61
    ||
    0.61
     Match
    0.60
    Act Density 0.089%

    No Known Activations