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

    Neuronpedia

    INDEX
    Explanations

    •

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roids
    -0.07
     constitutional
    -0.07
     NSArray
    -0.06
    account
    -0.06
     enactment
    -0.06
    icích
    -0.06
     performers
    -0.06
    testdata
    -0.06
     TArray
    -0.06
    -cn
    -0.06
    POSITIVE LOGITS
    identally
    0.07
     obsessive
    0.07
     conten
    0.07
     chế
    0.06
     pale
    0.06
     Girlfriend
    0.06
     khó
    0.06
     ipv
    0.06
    大学
    0.06
     ‏
    0.06
    Act Density 0.000%

    No Known Activations