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

    Neuronpedia

    INDEX
    Explanations

    statistical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    had
    -0.06
    laz
    -0.06
    ETweet
    -0.06
     に
    -0.06
     Brighton
    -0.06
     getColumn
    -0.06
    _true
    -0.06
    wechat
    -0.06
    dt
    -0.06
    ерим
    -0.06
    POSITIVE LOGITS
     frm
    0.07
     unified
    0.07
    _appro
    0.07
     Öğren
    0.06
     danger
    0.06
     inters
    0.06
    áv
    0.06
    ę
    0.06
    lov
    0.06
     Bound
    0.06
    Act Density 0.019%

    No Known Activations