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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Administr
    -0.07
     Features
    -0.07
    Administr
    -0.07
     dagen
    -0.07
     Flags
    -0.07
    delta
    -0.07
    Amenities
    -0.07
     days
    -0.07
    ാഴ്ച
    -0.07
     teammates
    -0.06
    POSITIVE LOGITS
     jeweils
    0.09
     νό
    0.09
     poderoso
    0.09
     уме
    0.09
    urion
    0.08
     herkennen
    0.08
    推广
    0.08
     рецепт
    0.08
     propon
    0.08
     подобрать
    0.08
    Act Density 0.025%

    No Known Activations