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

    Neuronpedia

    INDEX
    Explanations

    inside jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fujita
    0.42
     吸
    0.41
    অম
    0.38
     तल
    0.38
     समुदा
    0.38
    ИА
    0.37
    apol
    0.36
    ஞான
    0.35
    sunny
    0.35
     cristianos
    0.35
    POSITIVE LOGITS
     pee
    0.66
     Pee
    0.65
    pee
    0.48
     pecc
    0.47
     κινη
    0.46
    সিটি
    0.42
     obnoxious
    0.42
     piss
    0.40
     irregularities
    0.40
     Peanut
    0.39
    Act Density 0.001%

    No Known Activations