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

    Neuronpedia

    INDEX
    Explanations

    methods or guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     this
    -0.11
    This
    -0.09
     these
    -0.08
     This
    -0.07
    These
    -0.07
    SPAN
    -0.07
    this
    -0.07
     telegram
    -0.06
     독일
    -0.06
    Every
    -0.06
    POSITIVE LOGITS
    휴
    0.07
    основ
    0.06
     horsepower
    0.06
     आर
    0.06
     Passenger
    0.06
     Bond
    0.06
     │
    0.06
    _FORE
    0.06
     fought
    0.06
     vit
    0.06
    Act Density 0.063%

    No Known Activations