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

    Neuronpedia

    INDEX
    Explanations

    say "-"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oriented
    0.52
     oriented
    0.50
    ेंसिल
    0.49
     pairwise
    0.49
     radix
    0.49
    বিশিষ্ট
    0.48
     recursion
    0.47
     preamble
    0.47
     paragon
    0.47
     utterance
    0.46
    POSITIVE LOGITS
    -
    0.76
    ‑
    0.55
    ­
    0.52
    ־
    0.52
    ‌
    0.50
    
    0.47
    -;
    0.45
    ‐
    0.44
    ¬
    0.44
    odeficiency
    0.42
    Act Density 0.421%

    No Known Activations