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

    Neuronpedia

    INDEX
    Explanations

    debugging and error catching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Python
    0.45
    github
    0.43
    Data
    0.41
     Python
    0.41
    CSV
    0.40
    GitHub
    0.40
     Engine
    0.40
     CSV
    0.40
    File
    0.40
    Engine
    0.40
    POSITIVE LOGITS
    لک
    0.45
     marriages
    0.44
     matrimonio
    0.43
     costitu
    0.43
    юнча
    0.42
     luta
    0.42
     අඩු
    0.42
     கட்ட
    0.42
    рија
    0.42
     desarrollo
    0.41
    Act Density 0.013%

    No Known Activations