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

    Neuronpedia

    INDEX
    Explanations

    "that" followed by conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kes
    0.47
     Kes
    0.45
    T
    0.43
    Kes
    0.42
     Lup
    0.41
     פּ
    0.41
     F
    0.41
     Fl
    0.40
    زالة
    0.39
     Gre
    0.38
    POSITIVE LOGITS
    ouwd
    0.42
    ologisk
    0.41
    piratory
    0.41
    ücksicht
    0.41
     القيمه
    0.40
     supervision
    0.38
     supervised
    0.38
    ialog
    0.38
    價值
    0.38
     hervor
    0.38
    Act Density 0.000%

    No Known Activations