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

    Neuronpedia

    INDEX
    Explanations

    ring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bonded
    -0.07
     Bourbon
    -0.06
    芬
    -0.06
    -have
    -0.06
    combination
    -0.06
    -domain
    -0.06
    uncan
    -0.06
    -development
    -0.06
     Skype
    -0.06
    (pow
    -0.06
    POSITIVE LOGITS
     ortaya
    0.07
    观看
    0.07
     Predicate
    0.07
    Cover
    0.07
     sno
    0.07
     viewDidLoad
    0.06
    Kn
    0.06
    리스
    0.06
    .instructions
    0.06
     storefront
    0.06
    Act Density 0.031%

    No Known Activations