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

    Neuronpedia

    INDEX
    Explanations

    promises and pledges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orbent
    0.78
    interacting
    0.77
    परेट
    0.75
     extérieur
    0.74
     inquis
    0.74
    宦
    0.70
    Calc
    0.70
     Decimal
    0.69
     MRC
    0.69
     Selv
    0.68
    POSITIVE LOGITS
     promises
    2.39
     promise
    2.34
     Promises
    2.25
     Promise
    2.11
     pledges
    2.10
     pledge
    2.07
     commitment
    2.07
    promises
    2.04
    承诺
    2.02
    promise
    2.01
    Act Density 0.323%

    No Known Activations