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

    Neuronpedia

    INDEX
    Explanations

    follow-up studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manufact
    -0.08
    heat
    -0.07
     Praise
    -0.07
    _drv
    -0.07
    工
    -0.07
    '''↵↵
    -0.07
     manufactured
    -0.07
    製
    -0.07
     gearing
    -0.07
     мг
    -0.07
    POSITIVE LOGITS
     longitudinal
    0.13
    长期
    0.12
    Tracking
    0.12
     tracking
    0.12
     cohort
    0.12
     seguimiento
    0.11
     Tracking
    0.11
     acompanhamento
    0.11
     verfolgen
    0.11
     aging
    0.11
    Act Density 0.015%

    No Known Activations