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

    Neuronpedia

    INDEX
    Explanations

    math/logic problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flot
    -0.07
    _KEY
    -0.07
    디
    -0.07
     forgot
    -0.07
     étrange
    -0.07
     complied
    -0.07
    $route
    -0.07
    ennen
    -0.07
    keen
    -0.07
     overview
    -0.07
    POSITIVE LOGITS
     सप्त
    0.09
     الأحد
    0.09
     printk
    0.09
     začet
    0.08
     रविवार
    0.08
     সপ্ত
    0.08
     Нач
    0.08
     tjenester
    0.08
     diensten
    0.08
     بداية
    0.08
    Act Density 0.008%

    No Known Activations