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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ネル
    -0.06
     arma
    -0.06
     Sister
    -0.06
     Исп
    -0.06
     Willis
    -0.06
     roofing
    -0.06
     آباد
    -0.06
    (Schedulers
    -0.06
     Mazda
    -0.06
     schwer
    -0.06
    POSITIVE LOGITS
    Bundle
    0.07
    ién
    0.06
     undoubtedly
    0.06
     neutral
    0.06
    ată
    0.06
    YN
    0.06
    Το
    0.06
     ></
    0.06
    inness
    0.06
    vm
    0.06
    Act Density 0.505%

    No Known Activations