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

    Neuronpedia

    INDEX
    Explanations

    sentences that are product reviews that are somewhat positive, containing "is" and other value judgements

    oai_token-act-pair · gemini-2.0-flash

    keywords related to defining characteristics or attributes

    np_token-act-pair-logits · gpt-4o-mini

    code, summaries or reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.60
    WriteTagHelper
    -0.55
    Tis
    -0.46
     Meilleur
    -0.46
    EndContext
    -0.46
    InSection
    -0.46
    Pag
    -0.45
     ral
    -0.45
     الرياضيه
    -0.44
    global
    -0.44
    POSITIVE LOGITS
    Zitat
    0.60
    uxxxx
    0.57
    DEFIN
    0.56
    rrggbb
    0.56
    ReusableCell
    0.54
     réputation
    0.53
    คง
    0.52
    ioutil
    0.52
     defini
    0.51
     mía
    0.50
    Act Density 0.654%

    No Known Activations