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

    Neuronpedia

    INDEX
    Explanations

    except

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    心境
    -0.07
    收纳
    -0.07
     mắc
    -0.07
     Reese
    -0.06
     komen
    -0.06
    填补
    -0.06
     fram
    -0.06
    إرسال
    -0.06
     thiệt
    -0.06
    حضر
    -0.06
    POSITIVE LOGITS
    금
    0.07
     mortgages
    0.07
    戲
    0.07
     Rog
    0.07
    잦
    0.07
    timestamp
    0.07
     Trem
    0.07
     Welsh
    0.07
     thru
    0.07
    电话
    0.06
    Act Density 0.003%

    No Known Activations