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

    Neuronpedia

    INDEX
    Explanations

    monetary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prech
    -0.08
    Ferr
    -0.08
    /usr
    -0.07
     pel
    -0.07
     benöt
    -0.07
     blades
    -0.07
     silhou
    -0.07
     숙
    -0.07
     bessere
    -0.07
     chees
    -0.07
    POSITIVE LOGITS
     policies
    0.10
    政策
    0.10
     नीति
    0.09
    _policy
    0.09
     Policies
    0.09
    policy
    0.09
     auster
    0.08
     администрации
    0.08
     policy
    0.08
    Policies
    0.08
    Act Density 0.006%

    No Known Activations