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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    缫
    -0.07
    濞
    -0.07
    碚
    -0.06
    (.)
    -0.06
     shimmer
    -0.06
     scram
    -0.06
     Browse
    -0.06
     Scenes
    -0.06
     injustice
    -0.06
    大赛
    -0.06
    POSITIVE LOGITS
     excludes
    0.07
    联想
    0.07
    lambda
    0.07
    デン
    0.07
    可能会
    0.07
     XB
    0.07
    ülü
    0.06
     Trường
    0.06
     deux
    0.06
    都不
    0.06
    Act Density 0.329%

    No Known Activations