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

    Neuronpedia

    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UCE
    -0.07
     bondage
    -0.07
    boundary
    -0.06
     Cic
    -0.06
    stry
    -0.06
     mattered
    -0.06
    깨
    -0.06
     Suz
    -0.06
    _keys
    -0.06
    スク
    -0.06
    POSITIVE LOGITS
     report
    0.11
     Report
    0.11
    Report
    0.09
     reports
    0.09
    _report
    0.08
    report
    0.08
    보고
    0.08
    _Report
    0.07
    سات
    0.07
    ても
    0.07
    Act Density 0.022%

    No Known Activations