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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and words related to rankings

    oai_token-act-pair · gemini-2.0-flash

    terms indicating rankings or positions

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

    ranking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    saraba
    -0.69
    rénées
    -0.63
     الرياضيه
    -0.61
     lenker
    -0.59
    reportWebVitals
    -0.57
    RectangleBorder
    -0.53
    isfile
    -0.52
    Personensuche
    -0.51
    WriteBarrier
    -0.50
    TagMode
    -0.49
    POSITIVE LOGITS
     place
    0.89
     Place
    0.73
     PLACE
    0.65
    place
    0.61
    Place
    0.57
     Bioaccumulative
    0.57
    ElementException
    0.55
    出版年
    0.52
    PLACE
    0.52
     místo
    0.52
    Act Density 0.863%

    No Known Activations