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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dden
    -0.07
    ’)
    -0.07
     masih
    -0.06
     '),
    -0.06
     تهران
    -0.06
    "]
↵
    -0.06
     Rowling
    -0.06
    ient
    -0.06
     spiked
    -0.06
     ^{
    -0.06
    POSITIVE LOGITS
    "T
    0.06
     elevated
    0.06
    (Activity
    0.06
     environments
    0.06
     temperature
    0.06
     tipped
    0.06
     Parameters
    0.06
     Abram
    0.06
     Geo
    0.06
     wsp
    0.06
    Act Density 0.022%

    No Known Activations