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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    заб
    -0.07
     =~
    -0.06
     #
↵
    -0.06
    拍
    -0.06
    策
    -0.06
     ア
    -0.06
    pData
    -0.06
    ┐
    -0.06
    )!↵
    -0.06
    SerializeField
    -0.05
    POSITIVE LOGITS
    uyện
    0.07
     Traff
    0.07
     Faculty
    0.07
    ']]
    0.07
    query
    0.07
     resolution
    0.06
     resumed
    0.06
     behaviors
    0.06
     compute
    0.06
    ,status
    0.06
    Act Density 0.286%

    No Known Activations