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

    Neuronpedia

    INDEX
    Explanations

    face detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     msm
    -0.07
    реш
    -0.06
    .non
    -0.06
    ظم
    -0.06
     Commissioner
    -0.06
    ZH
    -0.06
     روشن
    -0.06
    	IN
    -0.06
     душ
    -0.06
     WM
    -0.06
    POSITIVE LOGITS
     Abrams
    0.06
    рав
    0.06
    (iParam
    0.06
     tượng
    0.06
    isas
    0.06
    COND
    0.06
    álně
    0.06
    �始化
    0.05
     eb
    0.05
    redit
    0.05
    Act Density 0.015%

    No Known Activations