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

    Neuronpedia

    INDEX
    Explanations

    Ending Value, Basic, Quality, Growth Rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     My
    0.40
    「
    0.37
     FBS
    0.36
    。
    0.36
     THAT
    0.35
     Lo
    0.35
     Aria
    0.34
     ж
    0.33
     The
    0.33
    ！
    0.33
    POSITIVE LOGITS
     keinen
    0.47
     এখানে
    0.45
    für
    0.45
    nitř
    0.44
     بالوں
    0.44
     प्रतिबंधित
    0.44
     Blumen
    0.43
    cadilly
    0.43
     വ്യക്ത
    0.43
    റോ
    0.43
    Act Density 0.000%

    No Known Activations