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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (selected
    -0.07
     Glover
    -0.07
    .Ref
    -0.07
     arrogance
    -0.06
    	im
    -0.06
    色
    -0.06
    	Error
    -0.06
     Dom
    -0.06
    раль
    -0.06
     Immediate
    -0.06
    POSITIVE LOGITS
     mutlaka
    0.07
    ainting
    0.07
     řád
    0.06
     dív
    0.06
    tery
    0.06
     توسعه
    0.06
     serene
    0.06
    _similarity
    0.06
     دف
    0.06
    ICATION
    0.06
    Act Density 0.002%

    No Known Activations