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

    Neuronpedia

    INDEX
    Explanations

    philosophers and thinkers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Proj
    0.86
     regelmatig
    0.83
     رپور
    0.83
    PSG
    0.79
    signale
    0.79
     fiets
    0.79
    ोरेंट
    0.79
     nova
    0.77
     Projekt
    0.76
     électronique
    0.76
    POSITIVE LOGITS
    Sl
    0.60
     failed
    0.58
     असफल
    0.58
     derived
    0.56
     heft
    0.55
    混ぜ
    0.55
     сю
    0.55
     suceder
    0.55
     Expo
    0.55
    科学家
    0.55
    Act Density 0.004%

    No Known Activations