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

    Neuronpedia

    INDEX
    Explanations

    starts of sentences after quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بشكل
    1.23
     vibe
    1.14
     timeframe
    1.00
     reboot
    1.00
     proactively
    0.98
     lifecycle
    0.96
     finalizing
    0.94
     proactive
    0.92
     revitalization
    0.91
     عندما
    0.91
    POSITIVE LOGITS
     thence
    1.16
     From
    0.93
     Many
    0.92
     mnoh
    0.90
     Surely
    0.90
     dahulu
    0.88
     It
    0.87
     But
    0.86
     Notwithstanding
    0.86
     Such
    0.86
    Act Density 0.057%

    No Known Activations