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

    Neuronpedia

    INDEX
    Explanations

    how it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     τρί
    0.46
     वेजिट
    0.40
    rir
    0.39
    กระท
    0.39
    แยก
    0.39
     карта
    0.38
     Comun
    0.38
     غرفة
    0.38
     спла
    0.37
    inom
    0.37
    POSITIVE LOGITS
    頤
    0.48
     >
    0.45
     ><
    0.43
    壽
    0.43
    熟悉的
    0.42
    |<
    0.42
     stateMutability
    0.42
    メニュー
    0.42
     ច
    0.42
     ကြ
    0.41
    Act Density 0.004%

    No Known Activations