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

    Neuronpedia

    INDEX
    Explanations

    instantiating exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     error
    0.46
    iles
    0.44
     Clients
    0.39
     Error
    0.39
     Runtime
    0.39
     masculin
    0.38
    incare
    0.38
    ινή
    0.38
     runtime
    0.37
     errors
    0.36
    POSITIVE LOGITS
    aggregate
    0.62
    Argument
    0.61
     Argument
    0.60
    Aggregate
    0.60
     Aggregate
    0.55
    Exception
    0.54
    FormatException
    0.54
     Exception
    0.51
     Exceptions
    0.50
     HttpRequest
    0.50
    Act Density 0.003%

    No Known Activations