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

    Neuronpedia

    INDEX
    Explanations

    object access operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Laravel
    0.95
    laravel
    0.90
     Symfony
    0.86
    Laravel
    0.76
     वेडिंग
    0.75
     ${{
    0.73
    Symfony
    0.72
     بخ
    0.72
    え
    0.71
    Goss
    0.71
    POSITIVE LOGITS
    ('_
    0.78
    ['
    0.77
    ['_
    0.75
     ['
    0.75
    iccation
    0.75
    uencias
    0.74
    вик
    0.73
    ulkner
    0.73
    load
    0.71
     connot
    0.70
    Act Density 0.036%

    No Known Activations