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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of lists or enumerations

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

    a list of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.51
     touché
    -0.44
     Hofmann
    -0.41
     Lehmann
    -0.41
     Rojas
    -0.41
     baixar
    -0.40
     traités
    -0.39
     inova
    -0.38
    touch
    -0.38
     perdana
    -0.37
    POSITIVE LOGITS
     list
    0.81
    SequentialGroup
    0.75
     lists
    0.69
    ListOf
    0.68
     liste
    0.67
     List
    0.67
     список
    0.62
     listado
    0.62
     Список
    0.61
     lista
    0.61
    Act Density 0.018%

    No Known Activations