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

    Neuronpedia

    INDEX
    Explanations

    URLs with "w"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Estonia
    -0.06
    Regular
    -0.06
     "."
    -0.06
     Jaguar
    -0.06
     {{{
    -0.06
     motors
    -0.06
     canopy
    -0.06
     texture
    -0.06
    Pedido
    -0.06
     command
    -0.06
    POSITIVE LOGITS
    (Input
    0.07
    ба
    0.07
     dw
    0.07
    惠
    0.06
     withheld
    0.06
     Shopping
    0.06
    φη
    0.06
    護
    0.06
     Reliable
    0.06
    dl
    0.06
    Act Density 0.009%

    No Known Activations