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

    Neuronpedia

    INDEX
    Explanations

    fading beam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вони
    0.50
    RECOMM
    0.45
    ุ
    0.45
    They
    0.44
     peasant
    0.44
    ారా
    0.41
    А
    0.41
    ού
    0.40
    водства
    0.40
     clueless
    0.40
    POSITIVE LOGITS
     Dise
    0.43
     cited
    0.42
     Treasure
    0.42
     utilised
    0.41
     Catalogue
    0.40
     Resources
    0.40
     KeyError
    0.38
    rizes
    0.38
     Gorge
    0.38
     Epsom
    0.38
    Act Density 0.003%

    No Known Activations