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

    Neuronpedia

    INDEX
    Explanations

    express or implied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extremities
    0.36
     Sometimes
    0.36
     spills
    0.36
     waterfalls
    0.35
    Sometimes
    0.34
    กัน
    0.33
     বাসিন্দা
    0.33
     \
    0.33
     sinks
    0.33
     resorts
    0.32
    POSITIVE LOGITS
     અથવા
    0.44
    atron
    0.42
     veya
    0.40
     কিংবা
    0.40
     ಅಥವಾ
    0.39
    anın
    0.38
    ari
    0.37
    ra
    0.37
    arzy
    0.37
     дизайна
    0.37
    Act Density 0.003%

    No Known Activations