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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     charge
    -0.09
     ड्र
    -0.08
     mengambil
    -0.08
    charge
    -0.08
    Charge
    -0.08
    -0.08
     placements
    -0.08
     Charge
    -0.08
     psi
    -0.07
     irr
    -0.07
    POSITIVE LOGITS
     Gast
    0.09
     Mothers
    0.08
     hallar
    0.08
     Dane
    0.08
     Cris
    0.08
     ţ
    0.08
     Gastr
    0.08
     Lips
    0.08
     Nuestro
    0.07
     ontstaan
    0.07
    Act Density 0.001%
    No Known Activations