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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     claws
    -0.07
    -hand
    -0.07
     anecd
    -0.07
     casual
    -0.07
     pauses
    -0.06
     XCTestCase
    -0.06
    ertiary
    -0.06
     Compet
    -0.06
     advocates
    -0.06
    14
    -0.06
    POSITIVE LOGITS
     printer
    0.06
     agricultural
    0.06
    _MOD
    0.06
     millones
    0.06
     shielding
    0.06
    .spi
    0.06
    μισ
    0.06
    untos
    0.05
     ACE
    0.05
     ";"
    0.05
    Act Density 0.023%

    No Known Activations