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

    Neuronpedia

    INDEX
    Explanations

    negative consequences and harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    事前
    0.75
    bleday
    0.73
    MenuItem
    0.72
     איך
    0.72
    שה
    0.70
     Fehler
    0.69
     Winning
    0.69
    cknowled
    0.69
     belirli
    0.68
     smiley
    0.68
    POSITIVE LOGITS
     psychological
    1.18
     disorientation
    1.16
     anxiety
    1.14
     psychosis
    1.14
     increased
    1.12
     destabil
    1.10
     inflammation
    1.09
     instability
    1.07
     malnutrition
    1.07
     disruption
    1.05
    Act Density 0.342%

    No Known Activations