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

    Neuronpedia

    INDEX
    Explanations

    4chan greentext

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🤩
    0.55
    ❣️
    0.49
     ডিভাইস
    0.47
    😊
    0.46
     equi
    0.45
    😍
    0.45
     offrir
    0.43
     бизне
    0.43
    ຈັດສົ່ງ
    0.43
    toare
    0.42
    POSITIVE LOGITS
     anon
    0.87
     anonymous
    0.86
     Anon
    0.86
     anonymity
    0.83
     Anonymous
    0.78
    Anon
    0.75
     anonymously
    0.75
    Anonymous
    0.72
     nihil
    0.64
    anonymous
    0.64
    Act Density 0.018%

    No Known Activations