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

    Neuronpedia

    INDEX
    Explanations

    address, events, files, story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hauptsächlich
    0.43
     உருவாக
    0.43
     fuer
    0.40
    pesar
    0.40
     tipos
    0.38
     часть
    0.38
     mostly
    0.37
     caract
    0.37
     ché
    0.37
     cult
    0.37
    POSITIVE LOGITS
    竞
    0.51
    phi
    0.46
     COMPET
    0.45
    𒋫
    0.43
    דע
    0.41
     сотрудни
    0.41
    市场上
    0.41
    Iowa
    0.40
     ফাইন
    0.40
    竞争
    0.39
    Act Density 0.207%

    No Known Activations