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

    Neuronpedia

    INDEX
    Explanations

    coordinate values and their manipulation in a coding context

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

    vector components like x, y, z

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.80
    transQ
    -0.79
     AssemblyCulture
    -0.79
    protoimpl
    -0.79
     BoxFit
    -0.78
    Autoritní
    -0.78
    <unused52>
    -0.77
    <unused17>
    -0.77
    <unused8>
    -0.77
    <pad>
    -0.77
    POSITIVE LOGITS
     pères
    0.39
     Hauteur
    0.37
     principaux
    0.35
     Sénat
    0.34
     lørdag
    0.34
     Gegensatz
    0.34
     Innenstadt
    0.33
     Mexique
    0.31
     désert
    0.31
     Longueur
    0.31
    Act Density 0.013%

    No Known Activations