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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inhibition
    -0.07
    開発
    -0.07
     Fak
    -0.06
     Audit
    -0.06
     Про
    -0.06
     VG
    -0.06
     Done
    -0.06
     finishing
    -0.06
    Fine
    -0.06
     flooded
    -0.06
    POSITIVE LOGITS
     monthly
    0.07
    vatel
    0.06
    TOCOL
    0.06
    DataSetChanged
    0.06
    getWindow
    0.06
     weekly
    0.06
    owy
    0.06
    getPage
    0.06
    arkin
    0.05
    іст
    0.05
    Act Density 0.002%

    No Known Activations