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

    Neuronpedia

    INDEX
    Explanations

    identifying digits in numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    운데
    -0.07
    -select
    -0.07
     tolerant
    -0.07
    ，从
    -0.06
     trays
    -0.06
    另一
    -0.06
    .gsub
    -0.06
     administrator
    -0.06
     Racing
    -0.06
    =key
    -0.06
    POSITIVE LOGITS
    ügen
    0.06
     damer
    0.06
    jl
    0.06
     Geek
    0.06
     Bord
    0.06
     blasted
    0.06
    phia
    0.06
    mark
    0.06
     unpredict
    0.06
     MB
    0.06
    Act Density 0.141%

    No Known Activations