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

    Neuronpedia

    INDEX
    Explanations

    examples and instances that highlight specific points or arguments

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

    an example of this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astéroïdes
    -0.45
     JAXBElement
    -0.41
    UrlResolution
    -0.39
    Autoritní
    -0.38
    parsedMessage
    -0.38
     typelib
    -0.36
    ベート
    -0.36
    brido
    -0.35
     oprot
    -0.35
    Bibitem
    -0.35
    POSITIVE LOGITS
    SequentialGroup
    0.63
     CURIAM
    0.48
    insatz
    0.47
    StandardCharsets
    0.47
     initComponents
    0.46
    staun
    0.46
    期刊论文
    0.45
    \{\\
    0.44
     akcji
    0.43
     Examples
    0.41
    Act Density 0.181%

    No Known Activations