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

    Neuronpedia

    INDEX
    Explanations

    scholarly publication metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Novels
    0.41
    petto
    0.40
     Winslow
    0.38
     भवि
    0.38
    ansky
    0.38
    workouts
    0.37
     offensively
    0.36
    newUser
    0.36
     जींस
    0.36
    故事
    0.36
    POSITIVE LOGITS
     DOI
    0.95
    DOI
    0.92
     doi
    0.86
    doi
    0.80
     arXiv
    0.79
     citation
    0.78
    PubMed
    0.77
    Abstract
    0.77
     PubMed
    0.76
     Citation
    0.73
    Act Density 0.008%

    No Known Activations