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

    Neuronpedia

    INDEX
    Explanations

    user engagement, time spent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inho
    -0.06
     intval
    -0.06
     본
    -0.06
     holdings
    -0.06
     Shields
    -0.06
     buffalo
    -0.06
     Harbor
    -0.06
     ря
    -0.06
     Buk
    -0.06
     Dent
    -0.06
    POSITIVE LOGITS
    LError
    0.06
     التر
    0.06
     परम
    0.06
     üye
    0.06
     profitability
    0.06
     پي
    0.06
     safety
    0.06
     dầu
    0.06
    .pat
    0.06
    ун
    0.06
    Act Density 0.014%

    No Known Activations