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

    Neuronpedia

    INDEX
    Explanations

    documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Á
    -0.07
     Sanctuary
    -0.07
    Integrity
    -0.07
    аша
    -0.07
     expertise
    -0.07
    Mor
    -0.07
     disparity
    -0.07
    Equality
    -0.07
    VM
    -0.07
     axi
    -0.07
    POSITIVE LOGITS
     divid
    0.10
     bezüglich
    0.09
     щодо
    0.09
     prehr
    0.09
    /calendar
    0.08
    下载安装
    0.08
     herunterladen
    0.08
     reale
    0.08
    覧
    0.08
     למה
    0.08
    Act Density 0.005%

    No Known Activations