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

    Neuronpedia

    INDEX
    Explanations

    Ottawa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strengthens
    -0.08
    Init
    -0.08
     demand
    -0.07
     strength
    -0.07
    announce
    -0.07
    ն
    -0.07
     yüks
    -0.07
    .sign
    -0.07
     jsonData
    -0.07
     succ
    -0.06
    POSITIVE LOGITS
     الإدارة
    0.07
    州市
    0.07
     😉
    0.07
    癿
    0.07
     DAMAGES
    0.07
    .BOTTOM
    0.07
    (browser
    0.07
     מאות
    0.07
     attackers
    0.07
     ancest
    0.06
    Act Density 0.002%

    No Known Activations