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

    Neuronpedia

    INDEX
    Explanations

    add ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     очень
    0.99
    Очень
    0.98
     дуже
    0.89
    qualität
    0.88
    beautiful
    0.87
    とても
    0.86
     wundersch
    0.86
     nagyon
    0.86
     rất
    0.86
     gewoon
    0.86
    POSITIVE LOGITS
     adjoining
    0.87
     aforesaid
    0.80
     недостатки
    0.80
     adjacent
    0.80
     diuretics
    0.78
     dismantling
    0.77
     beneath
    0.75
     suspicions
    0.75
     contingencies
    0.75
     автофо
    0.73
    Act Density 0.017%

    No Known Activations