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

    Neuronpedia

    INDEX
    Explanations

    /trunk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alborg
    -0.08
    照料
    -0.07
     Aydın
    -0.07
    *this
    -0.07
    楙
    -0.07
     Microsystems
    -0.07
     Camb
    -0.07
     долл
    -0.07
    牧场
    -0.06
    雅黑
    -0.06
    POSITIVE LOGITS
    数据
    0.07
    -rest
    0.07
    цен
    0.07
    Iter
    0.07
    𝑘
    0.07
     repetition
    0.07
     x
    0.07
    _Unit
    0.07
    几个人
    0.06
     pointers
    0.06
    Act Density 0.001%

    No Known Activations