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

    Neuronpedia

    INDEX
    Explanations

    emergencies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     долго
    -0.07
     doby
    -0.06
     Aurora
    -0.06
    _FORE
    -0.06
     Evropy
    -0.06
     gasoline
    -0.06
     Meyer
    -0.06
     origen
    -0.06
     FM
    -0.06
     очі
    -0.06
    POSITIVE LOGITS
     الصن
    0.08
    .middleware
    0.07
     Nich
    0.07
    ㅠㅠ
    0.07
     conceive
    0.07
    ñana
    0.06
    рупп
    0.06
    /categories
    0.06
    ник
    0.06
     BOTH
    0.06
    Act Density 0.029%

    No Known Activations