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

    Neuronpedia

    INDEX
    Explanations

    memorandum of understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }\
    -0.07
    部分
    -0.07
     bir
    -0.07
     Exhib
    -0.07
    兄
    -0.07
    貫
    -0.07
    strict
    -0.06
    計
    -0.06
    牧
    -0.06
     adherence
    -0.06
    POSITIVE LOGITS
    Newton
    0.07
    现代社会
    0.07
    龙泉
    0.07
    当成
    0.07
    afone
    0.07
    𬶟
    0.07
    neath
    0.07
     Geneva
    0.07
     helicopt
    0.07
     Maryland
    0.06
    Act Density 0.010%

    No Known Activations