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

    Neuronpedia

    INDEX
    Explanations

    Code, lists, formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gerichte
    -0.08
     NOTHING
    -0.08
    Closest
    -0.08
     swims
    -0.07
     stet
    -0.07
     esclus
    -0.07
     DIFFER
    -0.07
     stacks
    -0.07
    nothing
    -0.07
     wont
    -0.07
    POSITIVE LOGITS
    яўляецца
    0.08
     çäre
    0.08
    اسان
    0.08
     برنامج
    0.08
    macen
    0.08
     پروگرام
    0.08
    چا
    0.08
     besz
    0.08
    علام
    0.07
     البرنامج
    0.07
    Act Density 0.151%

    No Known Activations