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

    Neuronpedia

    INDEX
    Explanations

    poly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Serializer
    -0.07
     presenter
    -0.07
     Him
    -0.07
     ourselves
    -0.07
     booster
    -0.07
    Wr
    -0.07
     Saul
    -0.06
     Dr
    -0.06
    حر
    -0.06
     brought
    -0.06
    POSITIVE LOGITS
     poly
    0.10
    Poly
    0.09
     Poly
    0.07
    �
    0.07
    APolynomial
    0.07
    QUENCE
    0.07
    .itemView
    0.07
     Nichols
    0.07
     Complex
    0.07
    bitset
    0.07
    Act Density 0.025%

    No Known Activations