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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ControlItem
    -0.06
    AXB
    -0.06
    ousedown
    -0.06
     dps
    -0.06
     všech
    -0.06
    yp
    -0.06
     racks
    -0.06
     Shiv
    -0.06
     Nine
    -0.06
    029
    -0.06
    POSITIVE LOGITS
    ，就
    0.07
    WebKit
    0.07
    autos
    0.06
    .gl
    0.06
    pv
    0.06
     wreak
    0.06
    0.06
     misrepresented
    0.06
    DialogContent
    0.06
     Aleppo
    0.06
    Act Density 0.009%

    No Known Activations