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

    Neuronpedia

    INDEX
    Explanations

    users express opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PlayerDataCache
    0.42
    দর্শনে
    0.42
    లను
    0.42
    ভৃতি
    0.40
    κών
    0.39
    ফেসর
    0.38
    คโนโลยี
    0.38
    퓰
    0.38
    Quint
    0.37
    σεων
    0.37
    POSITIVE LOGITS
     shq
    0.41
     notes
    0.40
     exig
    0.40
     Warnings
    0.40
     inform
    0.39
     ala
    0.39
     knobs
    0.38
    atu
    0.38
    太郎
    0.38
     informs
    0.37
    Act Density 0.002%

    No Known Activations