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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (string
    -0.06
    ($"{
    -0.06
    dam
    -0.06
     STRING
    -0.06
    اوه
    -0.06
     sampling
    -0.06
    .Other
    -0.06
    FromArray
    -0.06
    UID
    -0.06
     adequ
    -0.06
    POSITIVE LOGITS
    уляр
    0.07
     каче
    0.07
    スター
    0.07
     Interesting
    0.06
     veri
    0.06
     [=[
    0.06
     Jenn
    0.06
     날
    0.06
     AssemblyFileVersion
    0.06
    знача
    0.06
    Act Density 0.111%

    No Known Activations