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

    Neuronpedia

    INDEX
    Explanations

    -app

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	EIF
    -0.08
     Monter
    -0.08
    ideos
    -0.08
    трад
    -0.08
    lace
    -0.08
    configs
    -0.07
    roit
    -0.07
     junge
    -0.07
    Carlos
    -0.07
    腐
    -0.07
    POSITIVE LOGITS
     holes
    0.08
    党和国家
    0.07
    ショップ
    0.07
    ❞
    0.07
    Times
    0.07
    endency
    0.07
    хот
    0.07
    //!
    0.06
     settling
    0.06
    🌲
    0.06
    Act Density 0.003%

    No Known Activations