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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	load
    -0.07
    	post
    -0.07
    	project
    -0.06
     Lowest
    -0.06
     posterior
    -0.06
     tặng
    -0.06
    _logged
    -0.06
     scratch
    -0.06
     coating
    -0.06
     AIDS
    -0.06
    POSITIVE LOGITS
    Phil
    0.06
     зер
    0.06
    meldung
    0.06
     Reaper
    0.06
     imageView
    0.06
    mir
    0.06
     recommendation
    0.06
    ів
    0.06
     Rosie
    0.06
     unarmed
    0.06
    Act Density 0.058%

    No Known Activations