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

    Neuronpedia

    INDEX
    Explanations

    old or traditional concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enumerate
    0.43
    ↵
    0.41
     bounded
    0.40
     으로
    0.39
    ="
    0.39
    """
    0.39
     Erika
    0.38
    \
    0.38
     `${
    0.38
     lunghezza
    0.37
    POSITIVE LOGITS
     old
    1.18
    fashioned
    1.05
     fashioned
    1.04
    旧
    0.98
     पुराने
    0.98
    old
    0.95
     vecchio
    0.94
     viejo
    0.93
    舊
    0.93
     OLD
    0.93
    Act Density 0.026%

    No Known Activations