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

    Neuronpedia

    INDEX
    Explanations

    words related to compensation, approval, and governance

    oai_token-act-pair · gemini-2.0-flash

    receive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.57
     دیکھیے
    -0.56
     conosciuto
    -0.50
     snippetHide
    -0.47
    ennale
    -0.47
     Darauf
    -0.45
    styleable
    -0.44
    <caption>
    -0.43
     conoció
    -0.43
     scoperto
    -0.43
    POSITIVE LOGITS
     lenker
    0.72
     Técnico
    0.57
    UAWEI
    0.56
     qashqai
    0.55
    ThroughAttribute
    0.54
     frågan
    0.52
    vér
    0.51
     barbati
    0.50
    AndEndTag
    0.50
     Argentino
    0.50
    Act Density 0.605%

    No Known Activations