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

    Neuronpedia

    INDEX
    Explanations

    elements related to rules or regulations in a procedural context

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

    Text after punctuation

    np_acts-logits-general · gemini-2.0-flash

    changes, ticket, have, neutral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dysfunction
    -0.48
    .
    -0.46
     Lombardi
    -0.45
    :
    -0.44
    menin
    -0.43
     concession
    -0.42
    ことがあります
    -0.42
     Tina
    -0.41
    اسف
    -0.41
    سكر
    -0.41
    POSITIVE LOGITS
     anyway
    0.88
    ftagPool
    0.86
     AssemblyCulture
    0.85
     chi̍t
    0.82
     ohnehin
    0.81
     anyways
    0.79
     etc
    0.78
     transfieras
    0.75
     anyhow
    0.73
    ArgsConstructor
    0.73
    Act Density 0.492%

    No Known Activations