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

    Neuronpedia

    INDEX
    Explanations

    IBM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ges
    -0.07
    .Round
    -0.07
     ethers
    -0.06
     rects
    -0.06
    .option
    -0.06
    paralle
    -0.06
    inflate
    -0.06
     Kre
    -0.06
    Square
    -0.06
     Stre
    -0.06
    POSITIVE LOGITS
     IBM
    0.09
     atm
    0.08
     Watson
    0.08
     ACM
    0.07
    IBM
    0.07
    VM
    0.07
     vm
    0.07
    posted
    0.07
    Im
    0.06
    vm
    0.06
    Act Density 0.008%

    No Known Activations