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

    Neuronpedia

    INDEX
    Explanations

    front

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mira
    -0.09
    inna
    -0.08
    pone
    -0.07
    uyện
    -0.07
    bonus
    -0.07
     Finans
    -0.07
    imine
    -0.07
    シリーズ
    -0.07
     рекомендуется
    -0.07
     scholarship
    -0.07
    POSITIVE LOGITS
     invading
    0.09
     unleashed
    0.08
    wech
    0.08
    aremment
    0.08
     conqu
    0.08
    Corporate
    0.08
     compr
    0.08
    .loads
    0.08
    Assim
    0.07
     Louisiana
    0.07
    Act Density 0.002%

    No Known Activations