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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pren
    0.81
    p
    0.81
    t
    0.80
    controls
    0.80
    a
    0.79
    le
    0.77
    fest
    0.72
    topping
    0.71
     catapult
    0.71
    step
    0.70
    POSITIVE LOGITS
     pathlib
    0.83
     productName
    0.80
     Advertisement
    0.78
     Wolves
    0.77
    ાર્થ
    0.76
    が多く
    0.75
     RegExp
    0.73
     Taxonomic
    0.73
     Suites
    0.72
     못한
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.