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

    Neuronpedia

    INDEX
    Explanations

    problems, failures, negative events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endphp
    -0.77
    CodeAttribute
    -0.74
    TestingModule
    -0.70
    IsContent
    -0.70
    UnitTesting
    -0.70
    IUrlHelper
    -0.70
     "..\..\
    -0.68
    __':
    -0.68
    __":
    -0.68
     jLabel
    -0.66
    POSITIVE LOGITS
    not
    0.59
     avoient
    0.55
    lt
    0.55
    kid
    0.54
     sélectionnés
    0.54
     étoient
    0.53
    long
    0.52
     Suivez
    0.52
     Monfieur
    0.52
    ons
    0.52
    Act Density 0.072%

    No Known Activations