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

    Neuronpedia

    INDEX
    Explanations

    business emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eca
    -0.07
    isicing
    -0.07
     lunches
    -0.06
    ani
    -0.06
    Dao
    -0.06
     Gandhi
    -0.06
     ramen
    -0.06
    .Domain
    -0.06
    acle
    -0.06
    西
    -0.06
    POSITIVE LOGITS
     dwar
    0.08
    (details
    0.06
    kses
    0.06
    صب
    0.06
     excitement
    0.06
     وضعیت
    0.06
     май
    0.06
     [↵
    0.06
     世界
    0.06
    —but
    0.06
    Act Density 0.205%

    No Known Activations