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

    Neuronpedia

    INDEX
    Explanations

    data dictionary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحم
    0.52
    郆
    0.50
     重要
    0.48
    㫻
    0.48
     QMessageBox
    0.48
    AllRef
    0.48
    㸳
    0.48
    дың
    0.48
    MemoryWarning
    0.48
    軎
    0.47
    POSITIVE LOGITS
    ↵
    0.65
    '
    0.53
     silver
    0.52
     database
    0.48
     sugar
    0.46
     soundtracks
    0.45
     carbon
    0.45
    ’
    0.45
    .
    0.45
     silber
    0.44
    Act Density 0.003%

    No Known Activations