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

    Neuronpedia

    INDEX
    Explanations

    exception handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bing
    0.82
    blind
    0.82
    율
    0.81
    ้อย
    0.81
     bonded
    0.81
    ní
    0.79
     corporal
    0.78
    شاه
    0.78
    &=
    0.77
     apprentices
    0.76
    POSITIVE LOGITS
     Exception
    1.43
    Exception
    1.32
     exception
    1.30
     Throwable
    1.24
    Throwable
    1.15
     excepciones
    1.09
     exceptions
    1.07
     excepción
    1.04
     erreur
    1.00
     HttpException
    0.98
    Act Density 0.021%

    No Known Activations