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

    Neuronpedia

    INDEX
    Explanations

    ?!

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vive
    -0.08
    Moved
    -0.08
     Liber
    -0.07
    잔
    -0.07
    -Free
    -0.07
    illow
    -0.07
    Products
    -0.07
    增长
    -0.07
    语文
    -0.07
    远洋
    -0.07
    POSITIVE LOGITS
    ≋
    0.07
    ราคา
    0.07
    meyeceği
    0.06
    □
    0.06
     Procedures
    0.06
    หลายๆ
    0.06
    مخاط
    0.06
     findings
    0.06
    מנהיג
    0.06
     Retry
    0.06
    Act Density 0.009%

    No Known Activations