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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻤ
    0.50
    များနှင့်
    0.47
     Buyers
    0.46
     nejsou
    0.45
     Emerging
    0.43
    ené
    0.43
     Interiors
    0.43
    ائو
    0.43
    𝗴
    0.43
     יותר
    0.43
    POSITIVE LOGITS
     അതിന്റെ
    0.62
     suas
    0.55
    はその
    0.54
     подтвер
    0.53
     dicha
    0.53
     endeavor
    0.50
     endeavors
    0.50
     pursuance
    0.50
     semblance
    0.49
     ihe
    0.49
    Act Density 0.000%

    No Known Activations