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

    Neuronpedia

    INDEX
    Explanations

    activities and plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Erickson
    0.54
     Topeka
    0.54
     automobile
    0.52
     remodeled
    0.50
     Gettysburg
    0.49
     DeConcini
    0.49
     automobiles
    0.49
    0.48
     geheel
    0.47
    ɚ
    0.47
    POSITIVE LOGITS
     dodgy
    0.84
     maths
    0.79
     cheeky
    0.75
     Lidl
    0.71
     WhatsApp
    0.70
     cosy
    0.69
     Spotify
    0.67
     Brexit
    0.67
     NHS
    0.67
     carers
    0.66
    Act Density 0.004%

    No Known Activations