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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     darkest
    -0.08
     dataset
    -0.07
    -stars
    -0.07
     enth
    -0.07
    marine
    -0.07
     swipe
    -0.07
     MyApp
    -0.07
    izzato
    -0.07
     выполн
    -0.07
     Almost
    -0.07
    POSITIVE LOGITS
    >false
    0.06
    **↵
    0.06
    ">'+
    0.06
    iter
    0.06
    neapolis
    0.06
    _ped
    0.06
    mé
    0.06
    ree
    0.06
    6
    0.06
    46
    0.06
    Act Density 0.086%

    No Known Activations