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

    Neuronpedia

    INDEX
    Explanations

    role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puedes
    -0.07
     cherry
    -0.06
    	fire
    -0.06
     keyed
    -0.06
     isten
    -0.06
    	base
    -0.06
    agnetic
    -0.06
    .imageView
    -0.06
    	params
    -0.06
     storms
    -0.06
    POSITIVE LOGITS
    Ens
    0.07
    ерим
    0.07
     administer
    0.06
    lobber
    0.06
    هم
    0.06
     modern
    0.06
    점
    0.06
    _GUI
    0.06
    Bio
    0.06
     CPR
    0.06
    Act Density 0.004%

    No Known Activations