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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amidst
    -0.07
     Η
    -0.06
     بور
    -0.06
     Heart
    -0.06
     euro
    -0.06
    ！」↵↵
    -0.06
     raise
    -0.06
    پ
    -0.06
    ンデ
    -0.06
     links
    -0.06
    POSITIVE LOGITS
    PERTY
    0.07
     предназнач
    0.06
    _MAT
    0.06
    acağım
    0.06
    ublic
    0.06
    ssue
    0.06
     보기
    0.06
     подготов
    0.06
     contacting
    0.06
     mẫu
    0.06
    Act Density 0.041%

    No Known Activations