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

    Neuronpedia

    INDEX
    Explanations

    Let's think step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rol
    1.22
     Wabash
    1.10
     NOM
    1.08
     Laf
    1.06
    Moody
    1.04
    Nob
    1.03
    rolle
    1.03
    NOM
    1.02
    Toc
    1.02
     Moody
    1.01
    POSITIVE LOGITS
    7
    1.41
     seventh
    0.88
    ７
    0.85
     seven
    0.79
    6
    0.78
    ७
    0.75
     seventy
    0.74
    ۷
    0.74
     ۷
    0.74
     Seven
    0.74
    Act Density 0.174%

    No Known Activations