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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .youtube
    -0.07
     Hole
    -0.07
    tearDown
    -0.07
    (userID
    -0.06
    istinguished
    -0.06
    赃
    -0.06
    enton
    -0.06
    ⵜ
    -0.06
    quit
    -0.06
     Dob
    -0.06
    POSITIVE LOGITS
    畦
    0.07
    ً
    0.07
    masına
    0.07
    던
    0.07
    巡察
    0.07
    �
    0.07
    اسب
    0.07
     contradictions
    0.07
     desp
    0.07
    桉
    0.07
    Act Density 0.041%

    No Known Activations