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

    Neuronpedia

    INDEX
    Explanations

    emotions and states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neur
    0.96
     proches
    0.95
     courte
    0.94
    eo
    0.89
     clothed
    0.87
     Eliot
    0.86
     flask
    0.86
     my
    0.85
     cache
    0.84
     callers
    0.84
    POSITIVE LOGITS
    ônia
    1.12
    ൽ
    1.09
    Proj
    1.07
    釉
    1.07
    Designing
    1.07
    ط
    1.06
    ّة
    1.05
     nhằm
    1.04
    技术的
    1.04
    ITY
    1.03
    Act Density 0.003%

    No Known Activations