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

    Neuronpedia

    INDEX
    Explanations

    Programming/data text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Suppliers
    -0.07
    emas
    -0.07
    mmo
    -0.07
    ав
    -0.07
     charms
    -0.07
     namespace
    -0.07
    Thr
    -0.07
     Africans
    -0.07
     transl
    -0.06
    lok
    -0.06
    POSITIVE LOGITS
    ETY
    0.08
    汧
    0.08
    ACHINE
    0.07
    ICLE
    0.07
     ');↵
    0.07
     onCancelled
    0.07
    .Stop
    0.07
    ATABASE
    0.07
     intrig
    0.07
    ATALOG
    0.07
    Act Density 0.048%

    No Known Activations