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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valves
    -0.07
     Ingredients
    -0.07
     Socialist
    -0.07
     multiple
    -0.07
     Properties
    -0.07
     addiction
    -0.07
    'im
    -0.07
     simp
    -0.07
     Reviewed
    -0.07
     enquiries
    -0.07
    POSITIVE LOGITS
    	bool
    0.07
     debtor
    0.06
    xfc
    0.06
    _row
    0.06
    tridge
    0.06
     camar
    0.06
    conds
    0.06
    _hpp
    0.06
     '^
    0.06
    confidence
    0.06
    Act Density 0.012%

    No Known Activations