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

    Neuronpedia

    INDEX
    Explanations

    Class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tunis
    -0.07
     journée
    -0.07
    	Toast
    -0.06
     Arbor
    -0.06
     Glas
    -0.06
     نبود
    -0.06
     wallets
    -0.06
     корп
    -0.06
    OSC
    -0.06
     răng
    -0.06
    POSITIVE LOGITS
    COMPLETE
    0.06
    容
    0.06
     modulation
    0.06
     sprites
    0.06
    _exempt
    0.06
    ?>
↵
    0.06
     loại
    0.06
    versible
    0.06
    مح
    0.06
    NESS
    0.06
    Act Density 0.002%

    No Known Activations