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

    Neuronpedia

    INDEX
    Explanations

    solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ais
    -0.09
    פי
    -0.08
    ാക്കള
    -0.08
    agasy
    -0.08
     policies
    -0.08
    policy
    -0.07
     rente
    -0.07
     decay
    -0.07
    aiser
    -0.07
    ಳೆ
    -0.07
    POSITIVE LOGITS
    症
    0.12
     symptoms
    0.11
    仍
    0.11
     المشكلة
    0.11
     symptômes
    0.11
     симптомы
    0.11
     مشکل
    0.11
     Persistent
    0.10
    Symptoms
    0.10
     проблему
    0.10
    Act Density 0.018%

    No Known Activations