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

    Neuronpedia

    INDEX
    Explanations

    Configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    决胜
    -0.08
    С
    -0.08
     Stub
    -0.07
    -disable
    -0.07
     consulate
    -0.07
     Usa
    -0.07
    שיתוף
    -0.07
    ún
    -0.07
    etu
    -0.07
     вес
    -0.07
    POSITIVE LOGITS
    添加剂
    0.06
    全校
    0.06
     aircraft
    0.06
    이라
    0.06
    	slot
    0.06
    "."
    0.06
     arteries
    0.06
    чин
    0.06
    android
    0.06
    cheduler
    0.06
    Act Density 0.001%

    No Known Activations