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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Disc
    -0.07
     obce
    -0.07
     ecs
    -0.07
     recre
    -0.06
    양
    -0.06
    」
    -0.06
    альное
    -0.06
    ी-
    -0.06
    摄
    -0.06
    iyoruz
    -0.06
    POSITIVE LOGITS
     equilibrium
    0.09
     poil
    0.07
    -topic
    0.06
    spark
    0.06
    !="
    0.06
     счита
    0.06
    ulur
    0.06
    :url
    0.06
    scious
    0.06
    ).
↵
    0.06
    Act Density 0.211%

    No Known Activations