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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sphere
    -0.07
    entario
    -0.06
    рук
    -0.06
    λη
    -0.06
    claration
    -0.06
     polarization
    -0.06
    ereotype
    -0.06
    Led
    -0.06
     storia
    -0.06
     período
    -0.06
    POSITIVE LOGITS
     advice
    0.06
     royal
    0.06
     Kickstarter
    0.06
     fla
    0.06
     Garn
    0.06
     sqrt
    0.06
     日本
    0.06
    SUMER
    0.06
    VIC
    0.06
     gameTime
    0.06
    Act Density 0.002%

    No Known Activations