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

    Neuronpedia

    INDEX
    Explanations

    backlinks at document bottom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    1.35
    enment
    1.25
    etop
    1.18
    ewhere
    1.09
    it
    1.07
    经历
    1.07
    יות
    1.03
    ك
    1.03
    טת
    1.03
    agory
    0.98
    POSITIVE LOGITS
    !!!!!
    1.53
    н
    1.40
     aet
    1.31
     लिए
    1.31
     altijd
    1.28
     ziyaret
    1.26
     شخصی
    1.24
     ander
    1.22
     sheer
    1.22
     insight
    1.21
    Act Density 0.000%

    No Known Activations