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

    Neuronpedia

    INDEX
    Explanations

    Cooking instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	In
    -0.07
     хроничес
    -0.07
     Kingdom
    -0.07
    widgets
    -0.07
    配
    -0.06
    _As
    -0.06
    .Inner
    -0.06
     inject
    -0.06
     ox
    -0.06
    klä
    -0.06
    POSITIVE LOGITS
    .depart
    0.07
     van
    0.06
    .star
    0.06
     Donate
    0.06
    рий
    0.06
     DLL
    0.06
     Saddam
    0.06
     chol
    0.06
    ,arg
    0.06
     Unsafe
    0.06
    Act Density 0.009%

    No Known Activations