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

    Neuronpedia

    INDEX
    Explanations

    activities and concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vet
    0.66
     office
    0.62
    MENT
    0.61
    ieck
    0.61
     light
    0.61
    مین
    0.61
     house
    0.61
    лда
    0.61
    ჯგუფი
    0.60
     LINE
    0.59
    POSITIVE LOGITS
    day
    0.76
     Circ
    0.75
     Tori
    0.72
    birds
    0.71
    zeug
    0.71
    puter
    0.71
    plan
    0.71
    bindings
    0.70
     Cir
    0.69
    bag
    0.69
    Act Density 0.137%

    No Known Activations