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

    Neuronpedia

    INDEX
    Explanations

    Repetition and habits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    爷
    -0.07
    company
    -0.06
    744
    -0.06
    142
    -0.06
      
    -0.06
     ra
    -0.06
    家
    -0.06
    Immediately
    -0.06
    Present
    -0.06
     Bearings
    -0.06
    POSITIVE LOGITS
    sci
    0.07
    .delay
    0.07
    aur
    0.07
    вест
    0.07
     qp
    0.07
    ��
    0.06
    雅黑
    0.06
    _GRAY
    0.06
    <B
    0.06
    (KP
    0.06
    Act Density 0.171%

    No Known Activations