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

    Neuronpedia

    INDEX
    Explanations

    associative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    涨
    -0.07
     cracks
    -0.06
     lacking
    -0.06
    线
    -0.06
    売
    -0.06
    由于
    -0.06
    免
    -0.06
     gradients
    -0.06
    /x
    -0.06
     scored
    -0.06
    POSITIVE LOGITS
    rabilir
    0.07
     translucent
    0.07
     lei
    0.07
     hij
    0.06
     beurette
    0.06
     Buddh
    0.06
     IDb
    0.06
     Feather
    0.06
    emin
    0.06
     cls
    0.06
    Act Density 0.003%

    No Known Activations