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

    Neuronpedia

    INDEX
    Explanations

    handling web requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    äle
    0.54
     Elytres
    0.54
    <unused235>
    0.50
    <unused2026>
    0.50
    <unused2027>
    0.50
     déprimées
    0.49
    positroid
    0.49
    <unused511>
    0.49
    reflectionMap
    0.48
    thisTrack
    0.48
    POSITIVE LOGITS
     Request
    0.86
     request
    0.78
    Request
    0.73
    request
    0.70
     headers
    0.68
     requests
    0.68
     REQUEST
    0.67
     Headers
    0.66
     Requests
    0.65
     req
    0.65
    Act Density 0.036%

    No Known Activations