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

    Neuronpedia

    INDEX
    Explanations

    component

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iếu
    -0.07
     اب
    -0.06
    	J
    -0.06
     Gow
    -0.06
    	dp
    -0.06
     interfer
    -0.06
     быстро
    -0.06
     qed
    -0.06
     conexion
    -0.06
    中文字幕
    -0.06
    POSITIVE LOGITS
    merc
    0.06
    imits
    0.06
     Fridays
    0.06
    _beh
    0.06
     oppress
    0.06
     mama
    0.06
    Chris
    0.06
     Hait
    0.06
    sei
    0.06
    antanamo
    0.06
    Act Density 0.010%

    No Known Activations