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

    Neuronpedia

    INDEX
    Explanations

    friendly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Column
    -0.07
    currentIndex
    -0.06
    賣
    -0.06
    home
    -0.06
     Vision
    -0.06
    --;↵↵
    -0.06
    INGTON
    -0.06
    ishops
    -0.06
     perverse
    -0.06
     Workout
    -0.06
    POSITIVE LOGITS
    LOSS
    0.07
    oji
    0.07
     gunfire
    0.06
    ytt
    0.06
     chased
    0.06
     регуляр
    0.06
    -tone
    0.06
     cheerful
    0.06
    葡
    0.06
    �
    0.06
    Act Density 0.017%

    No Known Activations