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

    Neuronpedia

    INDEX
    Explanations

    District

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    那一刻
    -0.07
    ASE
    -0.07
     새
    -0.07
     trivia
    -0.07
    畏
    -0.07
    Mark
    -0.07
    暗
    -0.06
    -em
    -0.06
    뼈
    -0.06
     ensured
    -0.06
    POSITIVE LOGITS
     diffic
    0.07
    主意
    0.07
    郸
    0.06
     woll
    0.06
    vinc
    0.06
    	rows
    0.06
     לבטל
    0.06
    俱乐
    0.06
    כונים
    0.06
     flats
    0.06
    Act Density 0.002%

    No Known Activations