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

    Neuronpedia

    INDEX
    Explanations

    steady

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ≪
    -0.08
     cellForRowAt
    -0.07
    ∅
    -0.07
     GRE
    -0.07
     ARG
    -0.07
    ជ
    -0.07
    奥林匹克
    -0.07
    horn
    -0.07
     blockbuster
    -0.06
     Filme
    -0.06
    POSITIVE LOGITS
     Needed
    0.08
    -mediated
    0.08
     steady
    0.08
    实
    0.07
     steadily
    0.07
     bande
    0.07
    ｐ
    0.07
    城墙
    0.07
    必要
    0.07
    Commerce
    0.07
    Act Density 0.005%

    No Known Activations