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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     siz
    -0.07
    ntity
    -0.07
     lợi
    -0.06
     cooper
    -0.06
     九
    -0.06
    };↵↵↵↵
    -0.06
     kvin
    -0.06
    ModelIndex
    -0.06
    004
    -0.06
     cookie
    -0.06
    POSITIVE LOGITS
    owany
    0.06
    áže
    0.06
     cages
    0.06
    روف
    0.06
    інг
    0.06
    еди
    0.06
    ?"
    0.06
     intervals
    0.06
    urved
    0.06
    WA
    0.06
    Act Density 0.141%

    No Known Activations