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

    Neuronpedia

    INDEX
    Explanations

    management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FACE
    -0.07
    oque
    -0.07
    istro
    -0.07
    ifold
    -0.07
     MART
    -0.07
     ren
    -0.06
     improv
    -0.06
     decentral
    -0.06
    ERGE
    -0.06
    一個
    -0.06
    POSITIVE LOGITS
    =q
    0.07
     QDialog
    0.07
     homemade
    0.06
    .Quad
    0.06
     disposing
    0.06
    .GetSize
    0.06
    uppies
    0.06
     Ag
    0.06
    vd
    0.06
    .priority
    0.06
    Act Density 0.008%

    No Known Activations