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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chahiye
    0.45
     turban
    0.45
    VICIO
    0.41
     salwar
    0.41
     acrylonitrile
    0.40
     えっと
    0.40
     Minaj
    0.40
     fifteenth
    0.39
     نيك
    0.39
    呛
    0.39
    POSITIVE LOGITS
    álni
    0.46
    ôle
    0.45
    ovane
    0.45
    ക്കുകയും
    0.42
    unctional
    0.42
    ăm
    0.41
    ੁਰ
    0.41
    Ა
    0.41
    ﻄ
    0.40
    دع
    0.39
    Act Density 0.001%

    No Known Activations