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

    Neuronpedia

    INDEX
    Explanations

    negative emotions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    öre
    0.64
    External
    0.61
     ette
    0.59
    Possible
    0.59
     apparently
    0.59
    Compliance
    0.58
     চলতি
    0.58
    apparently
    0.58
    ણે
    0.57
    Apparently
    0.57
    POSITIVE LOGITS
     jealousy
    0.97
     bullies
    0.96
     heartache
    0.90
     stealing
    0.89
     dissection
    0.84
     heartbreak
    0.84
     witnessing
    0.83
     scammers
    0.81
     prank
    0.81
     admiration
    0.80
    Act Density 0.000%

    No Known Activations