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

    Neuronpedia

    INDEX
    Explanations

    paid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lax
    -0.07
     songs
    -0.06
     lore
    -0.06
    Cad
    -0.06
    elters
    -0.06
     backstory
    -0.06
    ='/
    -0.06
    	PORT
    -0.06
     HID
    -0.06
     night
    -0.06
    POSITIVE LOGITS
     заклад
    0.07
     procure
    0.06
    977
    0.06
     Dragons
    0.06
    gew
    0.06
    spir
    0.06
     nedeni
    0.06
    terraform
    0.06
     때문에
    0.06
     اخت
    0.06
    Act Density 0.004%

    No Known Activations