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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     charger
    -0.06
    紅
    -0.06
    今年
    -0.06
     großen
    -0.06
     Wildcats
    -0.06
     Iv
    -0.06
    ทาน
    -0.06
    ژن
    -0.06
     plo
    -0.06
    ово
    -0.06
    POSITIVE LOGITS
     系
    0.06
     �
    0.06
     ﾉ
    0.06
    	tr
    0.06
    ..
    0.06
     Makeup
    0.06
     forms
    0.06
     scrapped
    0.06
    _empty
    0.06
    shopping
    0.06
    Act Density 0.051%

    No Known Activations