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

    Neuronpedia

    INDEX
    Explanations

    line, executed, unit, during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ॉरिटी
    0.38
    群体
    0.37
    ะ
    0.36
    समाज
    0.36
    堈
    0.36
    的人生
    0.36
    人生
    0.36
    桀
    0.35
    ホームページ
    0.34
    ี
    0.34
    POSITIVE LOGITS
     unit
    0.47
     during
    0.46
     and
    0.44
     During
    0.44
     cell
    0.42
     nucleotide
    0.40
     incident
    0.39
     data
    0.39
     executing
    0.39
     &
    0.39
    Act Density 0.727%

    No Known Activations