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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATERIAL
    -0.07
    *dt
    -0.07
    ITION
    -0.07
     ltd
    -0.07
    PIO
    -0.06
    Visited
    -0.06
    oxetine
    -0.06
    ندا
    -0.06
     глаза
    -0.06
    ее
    -0.06
    POSITIVE LOGITS
     Wikimedia
    0.06
     abuses
    0.06
     날
    0.06
    Assign
    0.06
     otherButtonTitles
    0.06
    _tl
    0.06
     Kullan
    0.06
    XX
    0.06
     agricult
    0.06
     Birch
    0.06
    Act Density 0.112%

    No Known Activations