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

    Neuronpedia

    INDEX
    Explanations

    descriptions and expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     envisaged
    0.72
     homely
    0.72
     orientated
    0.67
     inbuilt
    0.66
     Whilst
    0.65
     learnt
    0.64
     envisage
    0.64
     centimetres
    0.64
     centre
    0.64
     tyres
    0.63
    POSITIVE LOGITS
    Austin
    0.60
     bipartisan
    0.55
     outfitted
    0.54
    Seattle
    0.54
     appellate
    0.52
    Maui
    0.51
    Kyle
    0.51
    Kend
    0.49
     Stet
    0.49
    Nearly
    0.48
    Act Density 0.029%

    No Known Activations