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
    combat
    -0.07
    accumulator
    -0.06
     colony
    -0.06
    players
    -0.06
     breweries
    -0.06
    acles
    -0.06
     WEEK
    -0.06
    妮
    -0.06
     ammo
    -0.06
    unei
    -0.06
    POSITIVE LOGITS
     trustworthy
    0.06
     ребенка
    0.06
    のような
    0.06
    (Some
    0.06
    Rgb
    0.06
    都不
    0.06
    .any
    0.06
     eject
    0.06
     kimse
    0.06
    lcd
    0.06
    Act Density 0.072%

    No Known Activations