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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    compan
    -0.07
    .exec
    -0.07
     白
    -0.07
    toInt
    -0.07
    '):
    -0.07
     spraying
    -0.06
     prevalence
    -0.06
     underwear
    -0.06
     drafted
    -0.06
    minor
    -0.06
    POSITIVE LOGITS
     magnificent
    0.07
     맡
    0.06
     индивиду
    0.06
    .clientWidth
    0.06
     Anaheim
    0.06
     herald
    0.06
     Clarence
    0.06
    -American
    0.06
     nevertheless
    0.06
     Jeremiah
    0.05
    Act Density 0.093%

    No Known Activations