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

    Neuronpedia

    INDEX
    Explanations

    prime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disappeared
    -0.08
    expired
    -0.08
    /logger
    -0.06
     brawl
    -0.06
    έλ
    -0.06
    Warn
    -0.06
     Jest
    -0.06
     beat
    -0.06
    zk
    -0.06
     humans
    -0.06
    POSITIVE LOGITS
    送料
    0.07
     اروپ
    0.06
     refin
    0.06
    ประสบ
    0.06
    UINT
    0.06
    .cp
    0.06
    (elem
    0.06
     feasible
    0.06
     peny
    0.06
    规模
    0.06
    Act Density 0.002%

    No Known Activations