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

    Neuronpedia

    INDEX
    Explanations

    realistic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Artem
    -0.08
     переб
    -0.08
     Wil
    -0.08
     труд
    -0.08
     Пот
    -0.07
     zaak
    -0.07
     largely
    -0.07
     والسي
    -0.07
     alerted
    -0.07
     Minh
    -0.07
    POSITIVE LOGITS
    -looking
    0.09
     shot
    0.08
    -oriented
    0.08
    wissenschaft
    0.08
     skyscr
    0.08
     mundane
    0.08
    摄影
    0.08
     cliché
    0.08
     technological
    0.08
     outdoors
    0.08
    Act Density 0.005%

    No Known Activations