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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🏼
    -0.09
     escape
    -0.08
     sitcom
    -0.08
     pornography
    -0.07
    (det
    -0.07
    turn
    -0.07
    Eu
    -0.07
    🏻
    -0.07
     commonplace
    -0.07
     prevalence
    -0.07
    POSITIVE LOGITS
     Arrangement
    0.09
     venn
    0.09
     Circle
    0.09
     arranged
    0.09
     Council
    0.08
     আন্ত
    0.08
    _connections
    0.08
     Rings
    0.08
     círculo
    0.08
     interconnected
    0.08
    Act Density 0.020%

    No Known Activations