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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bad
    -0.07
    partners
    -0.07
    นค
    -0.06
     ec
    -0.06
    iolet
    -0.06
    ΟΚ
    -0.06
     ua
    -0.06
     CHO
    -0.06
     Floral
    -0.06
     isl
    -0.06
    POSITIVE LOGITS
    き
    0.07
    `↵
    0.06
    ılır
    0.06
    .widget
    0.06
    首页
    0.06
     istedi
    0.06
    gfx
    0.06
    /////////////////////////////////////////////////////////////////////////////↵
    0.06
     signs
    0.06
     upgrade
    0.06
    Act Density 0.002%

    No Known Activations