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

    Neuronpedia

    INDEX
    Explanations

    ol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivity
    -0.07
    .VALUE
    -0.07
    战士职业
    -0.07
    _Server
    -0.07
    (xhr
    -0.07
    ner
    -0.07
     MatDialog
    -0.07
    灌溉
    -0.07
    .view
    -0.07
    建筑业
    -0.07
    POSITIVE LOGITS
     Fin
    0.07
    的安全
    0.07
     ls
    0.07
     Committee
    0.07
     phil
    0.07
    \">
    0.06
     stretching
    0.06
    Unsafe
    0.06
     diplomacy
    0.06
     cop
    0.06
    Act Density 0.001%

    No Known Activations