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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Fi
    -0.08
     Streets
    -0.07
    墅
    -0.07
    善
    -0.07
    _coin
    -0.07
    沉积
    -0.07
    级别
    -0.06
     Abed
    -0.06
    厨师
    -0.06
     long
    -0.06
    POSITIVE LOGITS
    承接
    0.08
    枲
    0.07
    enerate
    0.07
     בארה
    0.07
     <>↵
    0.07
    镗
    0.07
    此举
    0.07
     pagina
    0.07
     decisión
    0.06
     OE
    0.06
    Act Density 0.002%

    No Known Activations