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

    Neuronpedia

    INDEX
    Explanations

    book titles and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lakini
    0.40
     なかっ
    0.39
     mutta
    0.38
    𒁉
    0.37
     atthakath
    0.36
    ลาคม
    0.35
     problémy
    0.35
     nhưng
    0.34
    ഫൈ
    0.34
     tačiau
    0.34
    POSITIVE LOGITS
     Houses
    0.41
    ’
    0.39
    are
    0.37
    S
    0.36
     Family
    0.36
     City
    0.36
     Health
    0.36
     Packaging
    0.35
    B
    0.35
     S
    0.35
    Act Density 0.001%

    No Known Activations