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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unfortunately
    -0.67
    Unfortunately
    -0.59
     unfortunately
    -0.56
     lamented
    -0.55
     Ironically
    -0.51
    anes
    -0.50
    genie
    -0.49
    Incident
    -0.49
    fortawesome
    -0.49
    Bis
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.94
     <=",
    0.90
     kasarigan
    0.86
     Paglinawan
    0.79
    LookAnd
    0.75
     للاسماء
    0.74
    aarrggbb
    0.74
    Demografie
    0.71
    IVEREF
    0.69
    Демографія
    0.67
    Act Density 0.644%

    No Known Activations