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

    Neuronpedia

    INDEX
    Explanations

    quality standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exas
    -0.07
    Objects
    -0.06
    -goal
    -0.06
     starvation
    -0.06
     Qin
    -0.06
    ynch
    -0.06
     rencont
    -0.06
    fusc
    -0.06
     тер
    -0.06
    タイプ
    -0.06
    POSITIVE LOGITS
    .","
    0.07
    APPED
    0.07
    raising
    0.07
    .Network
    0.07
     '\"
    0.06
    .Address
    0.06
    median
    0.06
     spine
    0.06
     hott
    0.06
     citing
    0.06
    Act Density 0.053%

    No Known Activations