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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,index
    -0.07
     is
    -0.06
    的小
    -0.06
    NewLabel
    -0.06
    eled
    -0.06
    셨
    -0.06
     khô
    -0.06
    Blockchain
    -0.06
     credibility
    -0.06
     Naughty
    -0.06
    POSITIVE LOGITS
     convention
    0.08
    isp
    0.07
    omore
    0.07
    ære
    0.06
    download
    0.06
    odore
    0.06
     Employer
    0.06
     ژانویه
    0.06
    wire
    0.06
    _managed
    0.06
    Act Density 0.005%

    No Known Activations