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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations, naming conventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMEN
    -0.54
    مصادر
    -0.53
     resourceCulture
    -0.52
     MenuView
    -0.50
    jsxFileName
    -0.50
    得上
    -0.49
    enziali
    -0.48
    ไหน
    -0.48
     UnityEditor
    -0.47
     Offizielle
    -0.47
    POSITIVE LOGITS
    "?>
    0.56
    TemporalType
    0.50
    bewerken
    0.48
    ecuted
    0.46
    parsedMessage
    0.46
    tesy
    0.46
    yq
    0.45
    Invoke
    0.44
     wikipagina
    0.43
    LBL
    0.43
    Act Density 0.001%

    No Known Activations