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

    Neuronpedia

    INDEX
    Explanations

    indicators of a formal or structured format, such as codes, identifiers, or programming syntax

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

    multilingual words or fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")){
    -0.77
     ModelExpression
    -0.71
     LoggerFactory
    -0.68
     saites
    -0.67
    ")));
    -0.66
    "])){
    -0.65
    (")");
    -0.64
    "]))
    -0.63
    "]];
    -0.63
    IonicModule
    -0.63
    POSITIVE LOGITS
     sogget
    0.66
     fortsatt
    0.55
    enterOuterAlt
    0.54
     fortfarande
    0.52
     naturali
    0.52
     Otro
    0.51
     artificiales
    0.51
    forChild
    0.51
     indé
    0.50
     automatiques
    0.50
    Act Density 0.032%

    No Known Activations