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

    Neuronpedia

    INDEX
    Explanations

    tiny homes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ണിക്ക
    0.45
     desar
    0.44
    り
    0.43
    ीत
    0.42
    ους
    0.41
    දහ
    0.41
    ټ
    0.41
    ක්
    0.41
    이지만
    0.41
    uß
    0.40
    POSITIVE LOGITS
     एक्सप्लेन
    0.46
     caveat
    0.46
     ดาว
    0.44
    蠍
    0.44
     چاہے
    0.44
     acoust
    0.44
     रिपोर्ट
    0.43
     имеют
    0.43
    Ear
    0.42
     ख़बर
    0.42
    Act Density 0.001%

    No Known Activations