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

    Neuronpedia

    INDEX
    Explanations

    held

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     南
    -0.08
    ��
    -0.07
    ))^
    -0.07
     tâm
    -0.07
     Hoy
    -0.06
     ｀
    -0.06
    kili
    -0.06
     exp
    -0.06
    _sum
    -0.06
    QP
    -0.06
    POSITIVE LOGITS
    uição
    0.06
    unded
    0.06
    ่าการ
    0.06
    گه
    0.06
    -sectional
    0.06
    -fe
    0.06
    -turn
    0.06
    ++){↵↵
    0.06
    recht
    0.06
    вы
    0.06
    Act Density 0.120%

    No Known Activations