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

    Neuronpedia

    INDEX
    Explanations

    arm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    兼
    -0.07
     Azerbai
    -0.07
     entertain
    -0.07
    投資
    -0.07
    而又
    -0.06
     stall
    -0.06
    হ
    -0.06
    乐视
    -0.06
    _frames
    -0.06
    .capitalize
    -0.06
    POSITIVE LOGITS
     IMPLEMENT
    0.07
    ضم
    0.07
    销售人员
    0.07
    ![↵
    0.07
    Dirty
    0.07
    le
    0.06
     formulate
    0.06
    QN
    0.06
     dolphin
    0.06
    穿上
    0.06
    Act Density 0.038%

    No Known Activations