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

    Neuronpedia

    INDEX
    Explanations

    initially

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urface
    -0.08
    package
    -0.08
    肆
    -0.07
    ວ
    -0.07
     setAddress
    -0.07
     �
    -0.07
    Vent
    -0.07
     Expect
    -0.07
     QHBoxLayout
    -0.06
    鬃
    -0.06
    POSITIVE LOGITS
    ראו
    0.08
    Officials
    0.07
    专班
    0.07
     controlled
    0.07
    与其
    0.07
     logs
    0.07
     stav
    0.07
     즉
    0.07
     temporary
    0.06
     chefs
    0.06
    Act Density 0.012%

    No Known Activations