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

    Neuronpedia

    INDEX
    Explanations

    logging and writing output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Biochemistry
    0.40
    坵
    0.39
     Herman
    0.38
     callSettings
    0.38
    燃烧
    0.38
     oiseaux
    0.37
    ிருக்கிறார்
    0.37
     equilibrated
    0.37
    してみてください
    0.37
     enfermedad
    0.37
    POSITIVE LOGITS
    log
    1.02
     log
    0.93
    Log
    0.91
     Log
    0.91
    ログ
    0.88
     logs
    0.86
    日志
    0.85
     logger
    0.80
     logging
    0.80
    logger
    0.77
    Act Density 0.036%

    No Known Activations