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

    Neuronpedia

    INDEX
    Explanations

    categories and genres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    包括
    0.42
    including
    0.40
    turbine
    0.39
     turbines
    0.36
    radeon
    0.35
     LEDs
    0.35
     включая
    0.35
     গ্রন্থে
    0.34
     wines
    0.33
     包括
    0.32
    POSITIVE LOGITS
     miscellaneous
    0.68
     Miscellaneous
    0.66
    Miscellaneous
    0.66
    misc
    0.61
     misc
    0.57
     Misc
    0.56
     Entertainment
    0.49
    Misc
    0.49
     Lifestyle
    0.49
     civic
    0.47
    Act Density 0.060%

    No Known Activations