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

    Neuronpedia

    INDEX
    Explanations

    datetime in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    трим
    0.40
    Lk
    0.40
    膜
    0.39
    制
    0.38
    WIS
    0.38
     制
    0.38
    गे
    0.38
     salons
    0.38
    承包人
    0.38
    ಮಾ
    0.37
    POSITIVE LOGITS
    Offset
    0.46
     offsets
    0.42
    オブジェクト
    0.42
     ngờ
    0.42
    对象
    0.41
     аль
    0.41
    naud
    0.40
    o
    0.40
     objects
    0.40
    ptic
    0.39
    Act Density 0.011%

    No Known Activations