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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     heartwarming
    0.81
     captivating
    0.80
     curfew
    0.76
     unassuming
    0.76
     Barangay
    0.75
     inclusivity
    0.74
     eCommerce
    0.73
    Cadastro
    0.72
     happenings
    0.72
     يُ
    0.71
    POSITIVE LOGITS
    methods
    0.63
    powerful
    0.61
     techniques
    0.60
    Methods
    0.60
    专门
    0.60
     methods
    0.59
     شیمی
    0.59
    called
    0.59
     técnicas
    0.59
    了一些
    0.59
    Act Density 12.986%

    No Known Activations