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

    Neuronpedia

    INDEX
    Explanations

    building and creating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buster
    -0.07
     bers
    -0.07
    irsch
    -0.07
     increased
    -0.07
     bel
    -0.07
     BG
    -0.07
    .Profile
    -0.07
     beat
    -0.07
    .AspNetCore
    -0.07
     airline
    -0.07
    POSITIVE LOGITS
    =-=-
    0.07
    =target
    0.07
     ورزش
    0.06
     Mostly
    0.06
     Adult
    0.06
     built
    0.06
    ])/
    0.06
    它
    0.06
    стро
    0.06
     Stam
    0.06
    Act Density 0.056%

    No Known Activations