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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veri
    -0.06
     tug
    -0.06
    Singleton
    -0.06
     Arrays
    -0.06
     multiply
    -0.06
     Wolfe
    -0.06
    Directed
    -0.06
     valid
    -0.06
     Several
    -0.06
    اور
    -0.06
    POSITIVE LOGITS
     Gover
    0.06
    (ids
    0.06
     Revised
    0.06
     */}↵
    0.06
    ανου
    0.06
    coord
    0.06
    атив
    0.06
     Bik
    0.06
    /admin
    0.06
    -reply
    0.06
    Act Density 0.013%

    No Known Activations