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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liberty
    -0.07
    енням
    -0.07
    83
    -0.06
    -engine
    -0.06
     missionary
    -0.06
    stances
    -0.06
    tar
    -0.06
    Impact
    -0.06
     ripping
    -0.06
    Kevin
    -0.06
    POSITIVE LOGITS
     zákon
    0.08
    ruits
    0.06
     neob
    0.06
     lining
    0.06
     txn
    0.06
    Values
    0.06
    CharCode
    0.06
    olland
    0.06
     amour
    0.06
    gregator
    0.06
    Act Density 0.047%

    No Known Activations