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

    Neuronpedia

    INDEX
    Explanations

    updates and announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     använda
    0.43
     attenuation
    0.43
    Use
    0.41
     disagreement
    0.41
     tolerated
    0.40
     lymphocyte
    0.40
     difficoltà
    0.40
     washers
    0.40
    Limitations
    0.40
     actuation
    0.40
    POSITIVE LOGITS
     updates
    0.88
     Updates
    0.87
     actualizaciones
    0.75
    updates
    0.70
    Updates
    0.68
     обновления
    0.68
     upcoming
    0.68
     अपडेट
    0.67
     announcements
    0.67
     Newsletter
    0.64
    Act Density 0.060%

    No Known Activations