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

    Neuronpedia

    INDEX
    Explanations

    easily followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ր
    0.71
    첵
    0.59
    ﻣ
    0.59
    कै
    0.58
     ከመ
    0.58
    सी
    0.57
    Ữ
    0.57
    ཇ
    0.57
     ပ
    0.56
    ᄄ
    0.56
    POSITIVE LOGITS
     fácil
    0.88
     fácilmente
    0.86
     easily
    0.80
    易
    0.75
    easily
    0.74
     facilmente
    0.73
     łat
    0.72
     easy
    0.71
     facilement
    0.71
     kolay
    0.71
    Act Density 0.171%

    No Known Activations