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

    Neuronpedia

    INDEX
    Explanations

    references to text-related properties and methods in code

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

    setting variable values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.92
    AddTagHelper
    -0.84
     betweenstory
    -0.83
     snippetHide
    -0.76
     '\\;'
    -0.75
     queſta
    -0.71
     XCTest
    -0.71
    Datuak
    -0.71
    ########.
    -0.70
    Tembelea
    -0.69
    POSITIVE LOGITS
     deportivo
    0.42
     conjunta
    0.42
     telefónica
    0.42
     precedentes
    0.40
     claramente
    0.40
     gruesa
    0.40
     correspondiente
    0.39
    .
    0.39
     colectiva
    0.39
     fotográfica
    0.38
    Act Density 0.003%

    No Known Activations