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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collaborate
    -0.07
     vocalist
    -0.07
    скор
    -0.07
    ลด
    -0.06
    uced
    -0.06
     Dir
    -0.06
    #ab
    -0.06
     yük
    -0.06
    	df
    -0.06
    求购
    -0.06
    POSITIVE LOGITS
     başarılı
    0.07
    ريل
    0.06
     muj
    0.06
     libert
    0.06
     onPause
    0.06
    .trailing
    0.06
    xee
    0.06
    .tele
    0.06
    [@"
    0.06
    内容
    0.06
    Act Density 0.017%

    No Known Activations