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

    Neuronpedia

    INDEX
    Explanations

    code-like segments including tags and variables

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.94
    Билгалдахарш
    -0.79
    ьаж
    -0.77
     Савезне
    -0.77
    ponses
    -0.73
    parsedMessage
    -0.72
    UserScript
    -0.67
    tvguidetime
    -0.67
    WithIOException
    -0.67
    protoimpl
    -0.66
    POSITIVE LOGITS
    dafx
    0.55
     Empres
    0.47
     देखा
    0.46
    下車
    0.45
    umumkan
    0.43
     tolu
    0.42
    tır
    0.41
    وير
    0.41
     लिया
    0.41
    ジラ
    0.40
    Act Density 0.242%

    No Known Activations