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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "abstract" and its variations in different contexts

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

    abstract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.61
    paravant
    -0.48
    Porsche
    -0.44
    thenReturn
    -0.44
     NVMe
    -0.44
     kWh
    -0.42
     Diony
    -0.42
    MessageTagHelper
    -0.41
    Leopard
    -0.41
    País
    -0.40
    POSITIVE LOGITS
    abstract
    1.16
     abstract
    1.01
    Abstract
    1.00
     Abstract
    0.95
     abstracts
    0.90
     ABSTRACT
    0.78
     Abstracts
    0.77
     abstrato
    0.75
    Abstracts
    0.72
     abstrait
    0.71
    Act Density 0.010%

    No Known Activations