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

    Neuronpedia

    INDEX
    Explanations

    Business products and services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voluntarily
    -0.06
    знач
    -0.06
     тя
    -0.06
    Chess
    -0.06
     анти
    -0.06
     modific
    -0.06
    unread
    -0.06
    -serving
    -0.06
    757
    -0.05
     TAM
    -0.05
    POSITIVE LOGITS
    --}}↵
    0.08
     weapon
    0.07
    	it
    0.07
    .boot
    0.07
     comes
    0.07
     biking
    0.07
    camera
    0.07
     panda
    0.07
    Grab
    0.06
    .vendor
    0.06
    Act Density 0.061%

    No Known Activations