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

    Neuronpedia

    INDEX
    Explanations

    special terms or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    src
    0.40
     зда
    0.39
    UpdatedAt
    0.39
    磯
    0.38
    xxxxxxxx
    0.38
    Hm
    0.38
    ডিস
    0.38
    ecd
    0.37
    Sdk
    0.37
    ধ্য
    0.37
    POSITIVE LOGITS
    opolis
    0.38
    кана
    0.38
    ͉
    0.37
     કેરી
    0.37
     Latitude
    0.37
    ارع
    0.36
     сообщение
    0.36
    褓
    0.36
     บ่
    0.36
     celebra
    0.36
    Act Density 0.000%

    No Known Activations