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

    Neuronpedia

    INDEX
    Explanations

    academic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Items
    -0.08
     הרבה
    -0.07
    蹭
    -0.07
     hu
    -0.07
    -budget
    -0.07
    שפע
    -0.07
    穷
    -0.07
    руз
    -0.06
    背叛
    -0.06
     trig
    -0.06
    POSITIVE LOGITS
     the
    0.08
    が
    0.08
    關於
    0.08
    habit
    0.08
    ,
    0.08
    돠
    0.08
     academic
    0.07
    の
    0.07
    住户
    0.07
    -hole
    0.07
    Act Density 0.008%

    No Known Activations