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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    也正是
    -0.07
     flash
    -0.07
    JoinColumn
    -0.07
    xce
    -0.07
    <meta
    -0.07
     zou
    -0.06
    /pi
    -0.06
    )Math
    -0.06
    getting
    -0.06
     vítima
    -0.06
    POSITIVE LOGITS
    ServiceProvider
    0.07
    Interstitial
    0.07
    oller
    0.07
    _brightness
    0.07
     ventil
    0.07
    装甲
    0.07
    _median
    0.07
    文娱
    0.06
     Enterprise
    0.06
    _system
    0.06
    Act Density 0.001%

    No Known Activations