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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     esposa
    -0.07
     risks
    -0.07
    DBC
    -0.07
    ्दर
    -0.07
    克斯
    -0.06
     ascending
    -0.06
    랙
    -0.06
    ึกษา
    -0.06
    abetic
    -0.06
     engaged
    -0.06
    POSITIVE LOGITS
     dpi
    0.06
     senha
    0.06
    writeln
    0.06
    	frame
    0.06
     �
    0.06
     欧美
    0.06
     FORCE
    0.06
    تب
    0.06
     tuto
    0.06
     зовніш
    0.06
    Act Density 0.010%

    No Known Activations