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

    Neuronpedia

    INDEX
    Explanations

    ordering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.73
     autorytatywna
    -0.69
    tagHelperRunner
    -0.67
    хьтан
    -0.65
    IUrlHelper
    -0.61
     glauben
    -0.57
    interopRequire
    -0.56
     émissions
    -0.56
    LLocation
    -0.56
     téléphonique
    -0.55
    POSITIVE LOGITS
     orders
    0.84
     ordered
    0.77
    Ordered
    0.61
    orders
    0.60
     Ordered
    0.60
    ordered
    0.60
     commands
    0.59
     ORDERED
    0.57
     commanded
    0.57
     Orders
    0.57
    Act Density 0.000%

    No Known Activations