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

    Neuronpedia

    INDEX
    Explanations

    shopping and dining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कृष्ण
    0.96
    mente
    0.89
    ടങ്ങ
    0.89
     žád
    0.88
    antes
    0.87
     واحد
    0.86
    stairs
    0.86
     shipping
    0.86
    èces
    0.86
    don
    0.85
    POSITIVE LOGITS
     Akira
    1.62
     brahm
    1.51
     intervalles
    1.46
    র
    1.45
    䖝
    1.44
     raindrops
    1.42
    rían
    1.41
    <unused616>
    1.40
     livelihoods
    1.40
     agonists
    1.39
    Act Density 0.000%

    No Known Activations