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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.09
     (
    -0.09
    id
    -0.08
    Chron
    -0.08
     dejar
    -0.07
    Blur
    -0.07
    Eff
    -0.07
    І
    -0.07
     близ
    -0.07
    Effect
    -0.07
    POSITIVE LOGITS
     adicionais
    0.11
     adicionales
    0.11
     supplémentaire
    0.10
     zusätzliche
    0.10
     부족
    0.10
     supplémentaires
    0.10
     additions
    0.09
     zusätzlichen
    0.09
     추가
    0.09
     अतिरिक्त
    0.09
    Act Density 0.014%

    No Known Activations