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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =$((
    -0.07
    Spark
    -0.07
     phiếu
    -0.07
     Spark
    -0.06
    finger
    -0.06
     proportion
    -0.06
    ḋ
    -0.06
    ro
    -0.06
    祂
    -0.06
    鄘
    -0.06
    POSITIVE LOGITS
    ]</
    0.07
    -the
    0.07
     Roku
    0.07
     ect
    0.07
    非常好
    0.07
     jeu
    0.07
    被害
    0.07
    妤
    0.07
    	packet
    0.07
     nest
    0.06
    Act Density 0.176%

    No Known Activations