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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urpose
    -0.07
    [p
    -0.06
    .cards
    -0.06
     Там
    -0.06
    readcrumb
    -0.06
    <T
    -0.06
     вперед
    -0.06
    /renderer
    -0.05
    =message
    -0.05
     lze
    -0.05
    POSITIVE LOGITS
     buoy
    0.06
     doctrines
    0.06
    ials
    0.06
    acy
    0.06
    ضة
    0.06
    μμα
    0.06
    (FALSE
    0.06
     efficacy
    0.06
    productive
    0.06
     privately
    0.06
    Act Density 0.016%

    No Known Activations