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

    Neuronpedia

    INDEX
    Explanations

    written by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    立马
    -0.07
    stmt
    -0.07
    שעה
    -0.07
    _Val
    -0.07
    艴
    -0.07
    اهل
    -0.07
    基本信息
    -0.07
    Monitor
    -0.07
     bfd
    -0.07
     Swal
    -0.07
    POSITIVE LOGITS
    Ӭ
    0.07
     Shan
    0.07
    一年
    0.06
    周恩
    0.06
    𝚑
    0.06
     loot
    0.06
    ציפ
    0.06
     Match
    0.06
     tiene
    0.06
     mixed
    0.06
    Act Density 0.037%

    No Known Activations