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

    Neuronpedia

    INDEX
    Explanations

    will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.47
    স্ট্র
    0.47
     水
    0.46
    ків
    0.45
    ：
    0.45
     একদিকে
    0.44
     więc
    0.43
    ؟
    0.43
    ？
    0.43
    ﻦ
    0.43
    POSITIVE LOGITS
    ponente
    0.46
     Bharatiya
    0.46
    volving
    0.46
    oretically
    0.46
    媜
    0.46
    ಗಳನ್ನು
    0.45
     Asociación
    0.45
    అ
    0.45
     Replies
    0.45
     multilateral
    0.44
    Act Density 0.136%

    No Known Activations