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

    Neuronpedia

    INDEX
    Explanations

    setup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isions
    -0.08
     Master
    -0.07
    itation
    -0.07
     Lord
    -0.07
     predictor
    -0.07
     rotating
    -0.07
    	random
    -0.07
    itations
    -0.07
    pectral
    -0.07
    ers
    -0.07
    POSITIVE LOGITS
     Setup
    0.10
     setup
    0.09
    setup
    0.08
     layout
    0.08
    ahat
    0.07
    システム
    0.07
     HQ
    0.07
     Оп
    0.07
    startup
    0.07
     Anaheim
    0.07
    Act Density 0.013%

    No Known Activations