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

    Neuronpedia

    INDEX
    Explanations

    places and descriptions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     digitalisation
    0.74
     Fuck
    0.70
     organiser
    0.66
     shortlisted
    0.66
     Maths
    0.65
     maths
    0.65
     diarrhoea
    0.65
     organisers
    0.64
     oraș
    0.64
     dodgy
    0.64
    POSITIVE LOGITS
     Adirond
    0.93
     Nantucket
    0.84
     historic
    0.82
     strolling
    0.81
     Gettysburg
    0.81
     Chesapeake
    0.80
     redwood
    0.79
     antiques
    0.76
     cottage
    0.75
     Americana
    0.75
    Act Density 0.070%

    No Known Activations