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

    Neuronpedia

    INDEX
    Explanations

    English dictionary and corpora

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encyclopedia
    0.58
     Encyclop
    0.57
     encycl
    0.53
     Encycl
    0.49
     энцикло
    0.47
    Encycl
    0.47
     Encyclopaedia
    0.46
    Encyclopedia
    0.45
     livro
    0.43
     panoram
    0.43
    POSITIVE LOGITS
     Papers
    0.44
    Papers
    0.40
     papers
    0.39
     Lemma
    0.39
     nef
    0.39
    papers
    0.37
     forb
    0.37
     oks
    0.37
     Royal
    0.37
     RNA
    0.37
    Act Density 0.000%

    No Known Activations