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

    Neuronpedia

    INDEX
    Explanations

    question mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bon
    -0.08
    actice
    -0.06
     Blanc
    -0.06
    ль
    -0.06
     помощ
    -0.06
    quiry
    -0.06
    Ing
    -0.06
    io
    -0.06
     країни
    -0.06
     نظامی
    -0.06
    POSITIVE LOGITS
     سبب
    0.07
    /security
    0.07
    _EXTRA
    0.06
    raises
    0.06
     awaits
    0.06
     �
    0.06
    _title
    0.06
     Jewish
    0.06
     MyClass
    0.06
    setVisibility
    0.06
    Act Density 0.002%

    No Known Activations