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

    Neuronpedia

    INDEX
    Explanations

    key terms related to research methodology and assessment

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    abstract concepts and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.53
    WebpackPlugin
    -0.48
    ViewFeatures
    -0.48
     themselves
    -0.47
     SafeMath
    -0.47
     was
    -0.46
    eynman
    -0.46
    怎么办
    -0.45
    lück
    -0.44
    encodeWith
    -0.43
    POSITIVE LOGITS
    AddHtmlAttribute
    0.79
    LEncoder
    0.76
    archiviato
    0.76
    ]--;
    0.73
     Paglinawan
    0.73
     abound
    0.71
    ÑOS
    0.66
     nakalista
    0.66
    ]='\
    0.66
     its
    0.65
    Act Density 0.416%

    No Known Activations