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

    Neuronpedia

    INDEX
    Explanations

    witnessing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .request
    -0.07
    <thead
    -0.06
    weekday
    -0.06
    ogenic
    -0.06
     UICollectionView
    -0.06
     ValueType
    -0.06
    _ob
    -0.06
     Suppress
    -0.06
     version
    -0.06
     bij
    -0.06
    POSITIVE LOGITS
     olup
    0.07
     závis
    0.07
    ταν
    0.07
     glow
    0.06
    avar
    0.06
     Dut
    0.06
    loh
    0.06
      ↵    ↵
    0.06
     DPR
    0.06
    0.06
    Act Density 0.033%

    No Known Activations