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

    Neuronpedia

    INDEX
    Explanations

    PL

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disagree
    -0.07
    quo
    -0.07
    回味
    -0.07
     Image
    -0.07
    implify
    -0.07
    赀
    -0.07
    מקד
    -0.06
    彻
    -0.06
    ⼊
    -0.06
    Discuss
    -0.06
    POSITIVE LOGITS
     brunette
    0.08
    储
    0.07
     akt
    0.07
     BG
    0.06
    HandlerContext
    0.06
     AT
    0.06
     CBC
    0.06
    Province
    0.06
    (Parse
    0.06
     readings
    0.06
    Act Density 0.000%

    No Known Activations