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

    Neuronpedia

    INDEX
    Explanations

    Mentions "or" and birds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dz
    -0.09
    %x
    -0.08
    sz
    -0.08
     trov
    -0.07
     katten
    -0.07
    OSS
    -0.07
     Kus
    -0.07
    猫
    -0.07
    ucking
    -0.07
     kat
    -0.07
    POSITIVE LOGITS
     contour
    0.09
     carbonate
    0.08
    Contour
    0.08
     turb
    0.08
     conforme
    0.08
    "|
    0.08
     अपर
    0.08
     transmis
    0.07
    0.07
    Commodity
    0.07
    Act Density 1.166%
    No Known Activations