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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    東京
    -0.06
     Surv
    -0.06
    驚
    -0.06
    ryan
    -0.06
     talk
    -0.06
     train
    -0.06
    хів
    -0.06
    骑
    -0.06
     college
    -0.06
     trans
    -0.06
    POSITIVE LOGITS
    0
    0.09
    .No
    0.07
    ο
    0.07
    o
    0.07
    .Cho
    0.07
    00
    0.07
    e
    0.07
     Sco
    0.07
    uo
    0.07
    avo
    0.07
    Act Density 0.027%

    No Known Activations