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

    Neuronpedia

    INDEX
    Explanations

    Units of time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Chham
    -0.45
    Edad
    -0.45
    DayOfWeek
    -0.45
    Fase
    -0.45
    Year
    -0.44
     pulumi
    -0.44
     setObject
    -0.44
     shui
    -0.43
    Nivel
    -0.43
    Dziękuję
    -0.43
    POSITIVE LOGITS
     Of
    0.68
     With
    0.56
    time
    0.56
    Of
    0.56
    attendre
    0.56
    ImageContext
    0.54
     Keeps
    0.53
     Consideration
    0.53
     Suff
    0.52
     Here
    0.52
    Act Density 0.649%

    No Known Activations