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

    Neuronpedia

    INDEX
    Explanations

    scientific publication names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    肐
    0.53
    쮿
    0.51
    Westinghouse
    0.51
    猊
    0.50
    ੴ
    0.48
    咉
    0.47
    鞆
    0.46
    奈川
    0.45
     കാല
    0.44
    鳧
    0.44
    POSITIVE LOGITS
     doi
    0.61
     microbiome
    0.54
     genomic
    0.53
     front
    0.52
    open
    0.52
    front
    0.51
     fronte
    0.50
     Frontiers
    0.50
     Article
    0.49
     frente
    0.48
    Act Density 0.003%

    No Known Activations