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

    Neuronpedia

    INDEX
    Explanations

    cast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ㏜
    -0.07
     SDLK
    -0.07
     supra
    -0.07
    Ɗ
    -0.07
    挟
    -0.07
    贫困村
    -0.07
    Ͼ
    -0.06
    PY
    -0.06
    .vert
    -0.06
     springfox
    -0.06
    POSITIVE LOGITS
     эконом
    0.07
     Switch
    0.07
    עני
    0.07
    魚
    0.07
    thumbnails
    0.07
     Public
    0.06
    שאיר
    0.06
     casinos
    0.06
     Lantern
    0.06
    כם
    0.06
    Act Density 0.005%

    No Known Activations