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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ద
    -0.07
     benöt
    -0.07
    海盗
    -0.07
    бед
    -0.07
     бесп
    -0.06
     bại
    -0.06
     deriving
    -0.06
    滾
    -0.06
    .Audio
    -0.06
     weak
    -0.06
    POSITIVE LOGITS
    embre
    0.07
    故乡
    0.07
    Age
    0.07
    世代
    0.07
    娘家
    0.06
    的时代
    0.06
    (players
    0.06
    裤子
    0.06
    (urls
    0.06
     Malone
    0.06
    Act Density 0.420%

    No Known Activations