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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anager
    -0.07
     سایت
    -0.07
    wner
    -0.06
     элемент
    -0.06
     gelen
    -0.06
    ální
    -0.06
    atural
    -0.06
    _SURFACE
    -0.06
     Sense
    -0.06
    яв
    -0.06
    POSITIVE LOGITS
    xb
    0.07
     七
    0.07
     čist
    0.06
    스코
    0.06
     실행
    0.06
     chức
    0.06
     실시
    0.06
     veget
    0.06
     incluso
    0.06
    GENER
    0.06
    Act Density 0.000%

    No Known Activations