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

    Neuronpedia

    INDEX
    Explanations

    pronoun then action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     £
    1.07
     Welsh
    0.87
     (£
    0.86
     Lancashire
    0.86
     బ్రి
    0.84
     Anglia
    0.82
     Merseyside
    0.81
     UK
    0.81
    £
    0.78
     Wales
    0.78
    POSITIVE LOGITS
     foreshadow
    0.83
     Dz
    0.79
     farewell
    0.78
    स्पून
    0.76
     Chuck
    0.75
    鈺
    0.74
     Golub
    0.73
    یاز
    0.71
    Tovar
    0.71
     canv
    0.70
    Act Density 0.012%

    No Known Activations