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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    built
    -0.58
    parsedMessage
    -0.57
     built
    -0.56
    classnames
    -0.55
    afficheront
    -0.55
     dibangun
    -0.55
    شاء
    -0.55
    orious
    -0.54
    oredCriteria
    -0.54
    build
    -0.53
    POSITIVE LOGITS
    TagHelper
    0.84
     nakalista
    0.63
     المعيارى
    0.59
     InputDecoration
    0.54
     concernés
    0.53
     connaissent
    0.52
     therefrom
    0.52
    CodedInputStream
    0.51
     Carga
    0.50
     marquées
    0.49
    Act Density 0.040%

    No Known Activations