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

    Neuronpedia

    INDEX
    Explanations

    Code/Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .material
    -0.07
     �
    -0.07
    def
    -0.07
     trunk
    -0.07
    	def
    -0.07
     الل
    -0.06
    registr
    -0.06
     eth
    -0.06
     çıkart
    -0.06
    marks
    -0.06
    POSITIVE LOGITS
    ﾊ
    0.06
    -II
    0.06
    .vel
    0.06
    /releases
    0.06
     miner
    0.06
     '#
    0.06
    leave
    0.06
     akıl
    0.06
    報
    0.06
    147
    0.06
    Act Density 0.017%

    No Known Activations