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

    Neuronpedia

    INDEX
    Explanations

    Relationships and infidelity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alls
    -0.07
    ermalink
    -0.07
     经
    -0.07
     университ
    -0.07
     Greenville
    -0.07
    _via
    -0.07
    났
    -0.07
    .trailingAnchor
    -0.06
     اخبار
    -0.06
    _ELEMENT
    -0.06
    POSITIVE LOGITS
     comme
    0.07
    τσ
    0.06
     occupies
    0.06
    traffic
    0.06
     applied
    0.06
    _as
    0.06
    siz
    0.06
    weather
    0.05
     DNS
    0.05
    頭
    0.05
    Act Density 0.014%

    No Known Activations