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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    овой
    -0.08
    ůl
    -0.07
    ulant
    -0.07
    벌
    -0.06
     lety
    -0.06
    .Modules
    -0.06
     ži
    -0.06
    眾
    -0.06
    面的
    -0.06
    aign
    -0.06
    POSITIVE LOGITS
    CHANGE
    0.07
     ihm
    0.07
     potřeb
    0.06
     пост
    0.06
     persistent
    0.06
    'RE
    0.06
    Paste
    0.06
     bara
    0.06
    Republic
    0.06
    .full
    0.06
    Act Density 0.000%

    No Known Activations