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

    Neuronpedia

    INDEX
    Explanations

    paragraph endings and/or beginnings of lists separated by spaces

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     незавершена
    -0.49
    <bos>
    -0.43
    eload
    -0.42
    parsedMessage
    -0.40
    fo
    -0.40
    -0.40
     allAfrica
    -0.40
    thon
    -0.39
    Referències
    -0.38
     مشين
    -0.38
    POSITIVE LOGITS
    ⓧ
    0.51
    httphttps
    0.49
    Fordítás
    0.44
    guenos
    0.42
    SharedDtor
    0.42
    zzleHttp
    0.41
     hanem
    0.40
    Spoljašnje
    0.40
    لكتر
    0.39
     насељу
    0.39
    Act Density 1.175%

    No Known Activations