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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -operative
    -0.08
    -Link
    -0.08
     aussehen
    -0.08
     avoidance
    -0.08
    ขึ้น
    -0.08
    aktionen
    -0.07
     empathy
    -0.07
    aktion
    -0.07
    aktions
    -0.07
     Crusher
    -0.07
    POSITIVE LOGITS
    traditional
    0.09
     преж
    0.08
    gos
    0.08
     traditionele
    0.08
    Ville
    0.08
     القديمة
    0.07
     شہر
    0.07
     hometown
    0.07
     phương
    0.07
     bearer
    0.07
    Act Density 0.036%

    No Known Activations