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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chanting
    -0.06
    rng
    -0.06
    ौज
    -0.06
    Floating
    -0.06
     Jedi
    -0.06
    egers
    -0.06
     bergen
    -0.06
    _bucket
    -0.06
    _login
    -0.06
    PLICIT
    -0.05
    POSITIVE LOGITS
    common
    0.09
    (origin
    0.07
    ómo
    0.07
     Grammy
    0.06
     marrying
    0.06
    aters
    0.06
    	On
    0.06
     flexDirection
    0.06
     (£
    0.06
     літ
    0.06
    Act Density 0.013%

    No Known Activations