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

    Neuronpedia

    INDEX
    Explanations

    data types and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    এল
    1.06
    ป็น
    1.05
     jeito
    1.03
    inactive
    1.03
     الن
    1.03
     بشكل
    1.03
     غير
    1.02
     العلمي
    1.02
     basit
    1.00
    急性
    1.00
    POSITIVE LOGITS
    /
    1.10
    )/
    1.08
    --)
    0.97
     Hinter
    0.87
    !)
    0.86
    &)
    0.86
     porter
    0.85
    ?)
    0.85
     fates
    0.84
    ),
    0.84
    Act Density 0.007%

    No Known Activations