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

    Neuronpedia

    INDEX
    Explanations

    specific aspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    們
    0.53
    ాను
    0.51
    /
    0.51
    Thousands
    0.47
    ইন
    0.47
    ির
    0.46
    ses
    0.46
    ภัย
    0.45
    しも
    0.44
    Timeout
    0.44
    POSITIVE LOGITS
    enov
    0.62
    zijde
    0.61
    ennessee
    0.60
    ของการ
    0.60
    ㎝
    0.60
     remittances
    0.59
    噌
    0.58
    𒁹
    0.57
     දක්
    0.57
     traveler
    0.57
    Act Density 1.351%

    No Known Activations