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

    Neuronpedia

    INDEX
    Explanations

    excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Banner
    -0.07
    ósito
    -0.06
     Hizmet
    -0.06
     Enough
    -0.06
    赖
    -0.06
     λόγ
    -0.06
     RECEIVER
    -0.06
     storia
    -0.06
     체
    -0.06
     Burl
    -0.06
    POSITIVE LOGITS
     연
    0.07
     ø
    0.07
    emma
    0.06
     Scholars
    0.06
    .setFocus
    0.06
    isActive
    0.06
    edu
    0.06
     allowable
    0.06
    .constraints
    0.06
     Spotify
    0.06
    Act Density 0.003%

    No Known Activations