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

    Neuronpedia

    INDEX
    Explanations

    stressful or upsetting situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pecados
    0.46
     criticality
    0.42
     tertarik
    0.41
     eccentricity
    0.39
     curiosity
    0.39
     /\
    0.38
     पीना
    0.38
     Redemption
    0.38
    興趣
    0.37
    rophy
    0.37
    POSITIVE LOGITS
     stressful
    1.88
     frustrating
    1.70
     distressing
    1.65
     upsetting
    1.54
     unsettling
    1.48
     exhausting
    1.41
     frightening
    1.33
     intimidating
    1.30
     painful
    1.30
     disturbing
    1.28
    Act Density 0.111%

    No Known Activations