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

    Neuronpedia

    INDEX
    Explanations

    scientific references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Division
    -0.06
    Perfect
    -0.06
     Provincial
    -0.06
    -ab
    -0.06
    仙
    -0.06
     Perfect
    -0.06
     Tacoma
    -0.06
     少
    -0.06
    ()['
    -0.06
    POSITIVE LOGITS
     batter
    0.06
    [((
    0.06
    ibt
    0.06
     propelled
    0.06
    currentTime
    0.06
     Tit
    0.06
    (worker
    0.06
     청
    0.06
     destroyer
    0.06
    ोद
    0.06
    Act Density 0.010%

    No Known Activations