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

    Neuronpedia

    INDEX
    Explanations

    modification, networks, complex models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     může
    0.44
     puedes
    0.42
     můžete
    0.41
     cartas
    0.41
     nincs
    0.41
     posibil
    0.40
     दिखाता
    0.39
     ricevuto
    0.39
     permita
    0.39
    襪
    0.39
    POSITIVE LOGITS
     calculation
    0.46
     calculations
    0.41
     rewrite
    0.39
     verification
    0.39
     initialization
    0.39
     cargar
    0.38
     reformulation
    0.38
    тод
    0.38
     logistical
    0.37
     actuar
    0.37
    Act Density 0.000%

    No Known Activations