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

    Neuronpedia

    INDEX
    Explanations

    #if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lon
    -0.07
     الدين
    -0.06
     טל
    -0.06
    长城
    -0.06
     לל
    -0.06
    &w
    -0.06
    옯
    -0.06
    龟
    -0.06
    家住
    -0.06
    +","+
    -0.06
    POSITIVE LOGITS
    绽放
    0.07
    ategories
    0.07
    であ
    0.07
     deepen
    0.07
     Sher
    0.07
     collaborate
    0.07
     Templates
    0.07
    "].
    0.07
     esper
    0.07
    אוניב
    0.07
    Act Density 0.001%

    No Known Activations