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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SG
    -0.07
    privileged
    -0.06
     devised
    -0.06
     임
    -0.06
     deren
    -0.06
     belong
    -0.06
     precarious
    -0.06
     parity
    -0.06
     mensagem
    -0.06
    /renderer
    -0.06
    POSITIVE LOGITS
    mon
    0.07
    �
    0.07
    904
    0.07
    ampled
    0.06
    ducible
    0.06
     dear
    0.06
    なん
    0.06
     सव
    0.06
    	cal
    0.06
     linear
    0.06
    Act Density 0.002%

    No Known Activations