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

    Neuronpedia

    INDEX
    Explanations

    Deborah

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Authenticate
    -0.07
     Mon
    -0.07
    <center
    -0.06
    SENT
    -0.06
     Authentication
    -0.06
     vente
    -0.06
    агато
    -0.06
    區
    -0.06
     entrepreneurship
    -0.06
    <ul
    -0.06
    POSITIVE LOGITS
     Eff
    0.07
     vk
    0.07
    Divider
    0.07
     Thema
    0.07
     ακ
    0.06
     dành
    0.06
     κρα
    0.06
    ากร
    0.06
     UPS
    0.06
     Tear
    0.06
    Act Density 0.001%

    No Known Activations