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

    Neuronpedia

    INDEX
    Explanations

    adventures, github, consideration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    th
    1.50
     meio
    1.41
    のである
    1.41
    ╅
    1.38
    the
    1.30
    እና
    1.30
     bungalows
    1.30
     année
    1.29
    s
    1.29
    ිබ
    1.27
    POSITIVE LOGITS
    лни
    1.41
    קו
    1.35
     Среди
    1.27
    ون
    1.16
    فظ
    1.15
     руководство
    1.11
     Такие
    1.10
    GetChar
    1.08
     Люди
    1.05
    PlainText
    1.05
    Act Density 0.000%

    No Known Activations