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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to emotional expressions or reactions

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

    Appears before paragraph numbers

    np_acts-logits-general · gemini-2.0-flash

    pterorum, opter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -1.01
    出版年
    -0.81
    alyptus
    -0.79
    esgue
    -0.72
     disambiguazione
    -0.70
    ValueStyle
    -0.69
     pinulongan
    -0.65
    -0.65
     Chwiliwch
    -0.64
    apunov
    -0.62
    POSITIVE LOGITS
    들
    0.82
    達
    0.72
    ów
    0.72
    lar
    0.71
    们
    0.70
    們
    0.70
    ů
    0.66
    々
    0.65
    들을
    0.63
    []
    0.62
    Act Density 0.070%

    No Known Activations