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

    Neuronpedia

    INDEX
    Explanations

    varying different things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    İ
    0.75
     numerous
    0.64
    Il
    0.64
    Ş
    0.61
     judge
    0.59
     package
    0.58
    Ç
    0.58
     luggage
    0.57
     performance
    0.57
     head
    0.55
    POSITIVE LOGITS
     ឬ
    0.66
    enem
    0.60
     수를
    0.60
     Buchstaben
    0.59
    ́p
    0.58
    ့်
    0.58
    orgung
    0.58
     vielf
    0.58
    ាស់
    0.57
     ಸ್ವಲ್ಪ
    0.57
    Act Density 0.035%

    No Known Activations