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

    Neuronpedia

    INDEX
    Explanations

    in-text citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    瞠
    0.35
    ियाणा
    0.34
     কথোপ
    0.34
    :'],
    0.34
     बीत
    0.34
    0.33
    ંમે
    0.33
    ⦁
    0.33
    วัสดี
    0.32
    కుంది
    0.32
    POSITIVE LOGITS
     cited
    0.59
     et
    0.55
     unpublished
    0.52
    cited
    0.50
     seminal
    0.47
     authors
    0.46
     eds
    0.46
    ).
    0.45
    authors
    0.43
     citado
    0.43
    Act Density 0.005%

    No Known Activations