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

    Neuronpedia

    INDEX
    Explanations

    -ification and Russian suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    łączy
    0.75
    的に
    0.75
     विभाजित
    0.71
    isticated
    0.70
     する
    0.70
     terminating
    0.68
     differentiating
    0.68
     communicating
    0.67
     interchangeable
    0.66
    भाषित
    0.66
    POSITIVE LOGITS
    ificación
    1.50
    ylation
    1.49
    ization
    1.49
    ification
    1.43
    ulation
    1.42
    ificazione
    1.41
    isation
    1.40
    шение
    1.40
    щение
    1.39
    жение
    1.39
    Act Density 0.289%

    No Known Activations