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

    Neuronpedia

    INDEX
    Explanations

    DEFAULT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    犁
    -0.07
    ThreadPool
    -0.07
     אותם
    -0.07
    !(:
    -0.07
    个百分点
    -0.07
    也只是
    -0.06
    .habbo
    -0.06
    ForgeryToken
    -0.06
    (DIR
    -0.06
    .callback
    -0.06
    POSITIVE LOGITS
    (schema
    0.07
     proximity
    0.07
    住宿
    0.07
    刺
    0.07
    对此
    0.06
    歷
    0.06
    أسلحة
    0.06
    }}"↵
    0.06
    -art
    0.06
     oxygen
    0.06
    Act Density 0.004%

    No Known Activations