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

    Neuronpedia

    INDEX
    Explanations

    concrete items and their state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disponíveis
    0.47
     available
    0.46
     disponibili
    0.46
     disponibles
    0.46
    品の
    0.45
    availability
    0.43
     disponibile
    0.42
    available
    0.41
     availability
    0.41
    AVAILABLE
    0.41
    POSITIVE LOGITS
    LLA
    0.43
     थी
    0.42
     peremptory
    0.41
    型的
    0.38
     regular
    0.38
     Stochastic
    0.37
     rounded
    0.37
     LRC
    0.37
    ক্ক
    0.37
     langu
    0.36
    Act Density 0.013%

    No Known Activations