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

    Neuronpedia

    INDEX
    Explanations

    compensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Arthur
    -0.07
    ήλ
    -0.07
    رود
    -0.07
     Arthur
    -0.07
     italiano
    -0.06
    Pt
    -0.06
     strut
    -0.06
     struk
    -0.06
    冷
    -0.06
    _chunk
    -0.06
    POSITIVE LOGITS
     compensation
    0.12
     compensate
    0.12
     Compensation
    0.11
     compens
    0.11
     compensated
    0.09
     useDispatch
    0.08
     salary
    0.07
    ам
    0.07
     exaggerated
    0.07
    ным
    0.07
    Act Density 0.004%

    No Known Activations