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

    Neuronpedia

    INDEX
    Explanations

    Styled

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _vertices
    -0.08
    花卉
    -0.08
    --,
    -0.07
    graphics
    -0.07
    韬
    -0.07
     vocabulary
    -0.07
    ירוש
    -0.07
    Ի
    -0.07
     Releases
    -0.07
    派遣
    -0.07
    POSITIVE LOGITS
     opted
    0.07
     PLUGIN
    0.06
    很长
    0.06
    AbsolutePath
    0.06
     Coupon
    0.06
    哪
    0.06
     ville
    0.06
    (tab
    0.06
     options
    0.06
     dint
    0.06
    Act Density 0.000%

    No Known Activations