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

    Neuronpedia

    INDEX
    Explanations

    Machine Learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifiques
    0.46
    anter
    0.46
    estern
    0.45
    é
    0.44
    esterly
    0.44
    élite
    0.43
    erol
    0.43
     بالغ
    0.43
     fasse
    0.42
    angered
    0.42
    POSITIVE LOGITS
     Lucifer
    0.51
     Donation
    0.50
     Yog
    0.49
    Donate
    0.49
    OLI
    0.48
     YEAR
    0.46
     Donate
    0.46
     Donations
    0.45
    پار
    0.45
     Chuck
    0.45
    Act Density 0.000%

    No Known Activations