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

    Neuronpedia

    INDEX
    Explanations

    exceptions and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     टक
    0.69
     aude
    0.65
     microcosm
    0.65
    loch
    0.63
     reconstituted
    0.62
     verand
    0.62
    жению
    0.62
    timeline
    0.61
     contenuto
    0.61
     collo
    0.60
    POSITIVE LOGITS
     exception
    2.22
    Exception
    2.14
     exceptions
    2.14
     Exception
    2.03
     error
    2.00
     Exceptions
    1.97
    ExceptionHandler
    1.94
    exceptions
    1.93
     catching
    1.92
    Exceptions
    1.92
    Act Density 1.193%

    No Known Activations