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

    Neuronpedia

    INDEX
    Explanations

    safety and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utt
    -0.08
    (Menu
    -0.08
     declar
    -0.08
     дов
    -0.08
    эс
    -0.08
    Restaurant
    -0.08
     repentance
    -0.07
    Xp
    -0.07
    Sorry
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    戴
    0.15
     gloves
    0.15
    佩
    0.14
     goggles
    0.14
     معدات
    0.13
     protecting
    0.13
     Protective
    0.13
     helmets
    0.13
     ochron
    0.13
     Protection
    0.12
    Act Density 0.062%

    No Known Activations