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

    Neuronpedia

    INDEX
    Explanations

    loved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.43
     पूरी
    0.43
    ̀u
    0.41
    V
    0.41
    R
    0.40
     पूरा
    0.40
    Yoga
    0.40
     नया
    0.40
     सिद्धांत
    0.40
     живут
    0.39
    POSITIVE LOGITS
    ﻻ
    0.38
     DON
    0.37
     decid
    0.36
     flound
    0.36
     in
    0.34
     loadings
    0.34
    _
    0.33
    َل
    0.33
    的山
    0.33
     Sql
    0.32
    Act Density 0.001%

    No Known Activations