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

    Neuronpedia

    INDEX
    Explanations

    authentic people adjacent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    提起
    0.45
     Ryanair
    0.45
     RSVP
    0.44
    際の
    0.43
    /
    0.43
    Terry
    0.43
     Kickstarter
    0.42
    Amanda
    0.42
    Penny
    0.42
     Granny
    0.41
    POSITIVE LOGITS
    leyball
    0.48
    ada
    0.47
     vorgesehen
    0.46
     जरुरी
    0.46
    ilen
    0.46
    adap
    0.46
     enriched
    0.45
     dipilih
    0.45
     zgodnie
    0.43
     οδη
    0.43
    Act Density 0.001%

    No Known Activations