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

    Neuronpedia

    INDEX
    Explanations

    showed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    826
    -0.07
    рин
    -0.07
    Jet
    -0.06
     indis
    -0.06
     Jamie
    -0.06
    ΙΣ
    -0.06
    обы
    -0.06
     inquiries
    -0.06
     connexion
    -0.06
    Monkey
    -0.06
    POSITIVE LOGITS
    %)↵↵
    0.06
    .glob
    0.06
    .boot
    0.06
     chce
    0.06
    ประช
    0.06
     trait
    0.06
    uable
    0.06
    ｗ
    0.06
    __*/
    0.06
     países
    0.06
    Act Density 0.027%

    No Known Activations