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

    Neuronpedia

    INDEX
    Explanations

    graphene and medical relief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eigenstates
    1.50
    𝗡
    1.42
    𝗬
    1.39
     annealing
    1.35
    𝗟
    1.34
     anode
    1.33
     cadmium
    1.32
     Fonction
    1.26
     chloro
    1.24
     neodymium
    1.24
    POSITIVE LOGITS
    ei
    1.28
    p
    1.17
    ora
    1.14
    ones
    1.11
    ot
    1.10
    ve
    1.10
    e
    1.08
    пе
    1.07
    m
    1.06
    een
    1.06
    Act Density 0.001%

    No Known Activations