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

    Neuronpedia

    INDEX
    Explanations

    journalism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    
    -0.07
    carousel
    -0.06
    .Clamp
    -0.06
     Raptors
    -0.06
    _sources
    -0.06
     CES
    -0.06
    eree
    -0.06
     NPCs
    -0.06
     Foreign
    -0.06
     humane
    -0.06
    POSITIVE LOGITS
    стю
    0.07
    running
    0.06
    pos
    0.06
     "..
    0.06
    魂
    0.06
    azon
    0.06
    	item
    0.06
    emails
    0.06
     вмі
    0.06
    (region
    0.06
    Act Density 0.010%

    No Known Activations