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

    Neuronpedia

    INDEX
    Explanations

    goals or targets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Certain
    -0.07
    addAction
    -0.06
    "?>↵
    -0.06
    _GPIO
    -0.06
     кар
    -0.06
     상대
    -0.06
     accusations
    -0.06
    िनक
    -0.06
     STAT
    -0.06
    Instructions
    -0.06
    POSITIVE LOGITS
     kans
    0.06
    방송
    0.06
    ob
    0.06
    .typ
    0.06
    valuate
    0.06
    akin
    0.06
     Phys
    0.06
    违
    0.06
     горм
    0.06
    окрем
    0.06
    Act Density 0.367%

    No Known Activations