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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Canvas
    -0.07
    primitive
    -0.06
     إطار
    -0.06
     значит
    -0.06
    -containing
    -0.06
    麼
    -0.06
    粮食
    -0.06
    rish
    -0.06
     qualità
    -0.06
    (patient
    -0.06
    POSITIVE LOGITS
    ADF
    0.07
     arrog
    0.07
    鹫
    0.07
    )'),
    0.07
    填写
    0.07
    酸奶
    0.07
    ","
    0.07
    做大做强
    0.06
    ⓜ
    0.06
    apol
    0.06
    Act Density 0.067%

    No Known Activations