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

    Neuronpedia

    INDEX
    Explanations

    high society

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &_
    -0.07
     Benson
    -0.07
     woo
    -0.06
    "`↵↵
    -0.06
    působ
    -0.06
     الله
    -0.06
     Books
    -0.06
    clk
    -0.05
     plaisir
    -0.05
    ("'",
    -0.05
    POSITIVE LOGITS
    /testify
    0.07
     perish
    0.06
     sector
    0.06
    าศ
    0.06
    tron
    0.06
     protective
    0.06
     flu
    0.06
    えば
    0.06
     Confirm
    0.06
    국
    0.06
    Act Density 0.105%

    No Known Activations