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

    Neuronpedia

    INDEX
    Explanations

    street signs and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genome
    0.66
     Epid
    0.58
     essential
    0.56
     essentielles
    0.56
    сера
    0.55
    elung
    0.54
     anions
    0.54
     essentiels
    0.54
    plist
    0.53
    ান্ত
    0.53
    POSITIVE LOGITS
     Straße
    0.78
     samoch
    0.74
     porch
    0.74
     roads
    0.73
     Road
    0.73
    streetlight
    0.73
     porches
    0.71
     Đường
    0.70
     storefront
    0.70
     pojem
    0.68
    Act Density 0.267%

    No Known Activations