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

    Neuronpedia

    INDEX
    Explanations

    Control, dominance, possession

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encoder
    -0.07
     decade
    -0.07
     USERS
    -0.07
    (Session
    -0.07
    หล
    -0.07
     Pittsburgh
    -0.06
    GOR
    -0.06
    “My
    -0.06
    Spaces
    -0.06
    ellen
    -0.06
    POSITIVE LOGITS
    (deg
    0.08
     culp
    0.07
     西
    0.06
    asionally
    0.06
     Styles
    0.06
    柄
    0.06
    	hr
    0.06
    sr
    0.06
    (m
    0.06
     fle
    0.06
    Act Density 0.004%

    No Known Activations