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

    Neuronpedia

    INDEX
    Explanations

    or null or conditional return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mengatur
    0.46
    toare
    0.42
     обеспечить
    0.40
     jeg
    0.40
     számára
    0.40
     කිරීමට
    0.38
     memeriksa
    0.38
     perlu
    0.38
     reforzar
    0.38
     सुझाव
    0.37
    POSITIVE LOGITS
     oppure
    0.59
     null
    0.54
    null
    0.51
    Null
    0.48
     หรือ
    0.46
     Or
    0.45
     或者
    0.45
    거나
    0.45
    NULL
    0.45
     অথবা
    0.45
    Act Density 0.073%

    No Known Activations