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

    Neuronpedia

    INDEX
    Explanations

    answer instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वेळ
    0.41
    与之
    0.40
     হাসি
    0.40
     miliardi
    0.40
     матери
    0.39
     گیری
    0.38
     lép
    0.38
     पल
    0.37
     दुप
    0.36
    뤼
    0.36
    POSITIVE LOGITS
    Fon
    0.42
     fon
    0.40
     Fon
    0.38
    pct
    0.38
    fon
    0.38
    tgz
    0.37
     Office
    0.37
     folgende
    0.37
    shortcuts
    0.37
     folgenden
    0.36
    Act Density 0.004%

    No Known Activations