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

    Neuronpedia

    INDEX
    Explanations

    different forms of quotation marks and dialogue indicators

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

    quote punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.83
    ftagPool
    -0.65
    invokeLater
    -0.60
     imagui
    -0.59
    RegressionTest
    -0.59
     }}$}
    -0.57
    verwijspagina
    -0.57
    IUrlHelper
    -0.57
     queſta
    -0.56
    ″]
    -0.56
    POSITIVE LOGITS
     olup
    0.36
     obrazu
    0.34
     muerto
    0.33
     cioè
    0.33
     aprobación
    0.31
    ...
    0.31
     said
    0.31
    ,
    0.30
     linkovi
    0.29
     inscripción
    0.29
    Act Density 0.018%

    No Known Activations