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

    Neuronpedia

    INDEX
    Explanations

    performance highlights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WHEN
    0.90
     있으면
    0.89
     wanneer
    0.86
     whenever
    0.86
     hypothetical
    0.83
     isActive
    0.82
     plaus
    0.81
    hankelijk
    0.79
    whenever
    0.76
     chce
    0.75
    POSITIVE LOGITS
     destaque
    1.23
    Highlights
    1.05
    Despite
    1.04
    Результа
    1.00
     Despite
    1.00
    Surprisingly
    1.00
     Несмотря
    0.97
     despite
    0.96
    Results
    0.96
    Team
    0.94
    Act Density 0.091%

    No Known Activations