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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "_
    0.43
     thistle
    0.42
     gingham
    0.41
     creates
    0.40
    粉
    0.40
     Comet
    0.39
     Cutter
    0.39
     saw
    0.39
    采
    0.39
     Cyst
    0.38
    POSITIVE LOGITS
     ova
    0.50
    aktoren
    0.49
    لين
    0.47
    خ
    0.47
     ingresso
    0.46
    ী
    0.43
    О
    0.43
    в
    0.43
     যাওয়ার
    0.42
     atas
    0.42
    Act Density 0.006%

    No Known Activations