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

    Neuronpedia

    INDEX
    Explanations

    Interval intersections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یب
    -0.09
    -budget
    -0.09
    ότητες
    -0.09
     पैसा
    -0.09
     FIFA
    -0.09
     budget
    -0.08
    投入
    -0.08
    CRYPT
    -0.08
     حتی
    -0.08
     செல
    -0.08
    POSITIVE LOGITS
     boundaries
    0.08
    _union
    0.08
     Haus
    0.08
     üy
    0.08
     террит
    0.08
     영역
    0.08
     Users
    0.08
    เอ
    0.08
     supprimer
    0.07
     unsubscribe
    0.07
    Act Density 0.034%

    No Known Activations