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

    Neuronpedia

    INDEX
    Explanations

    Code comparing numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     antid
    -0.08
    媄
    -0.07
    מנ
    -0.07
    좡
    -0.07
    吲
    -0.07
    挽
    -0.07
     Mini
    -0.07
    塅
    -0.06
    しっ
    -0.06
    .descripcion
    -0.06
    POSITIVE LOGITS
    ophile
    0.09
     history
    0.08
     была
    0.07
    itia
    0.07
     !!!
    0.07
    以後
    0.07
     Lighting
    0.07
    year
    0.06
    字体
    0.06
    ller
    0.06
    Act Density 0.019%

    No Known Activations