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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     తెలిపారు
    0.25
    ၜ
    0.25
     تھے۔
    0.23
    ومات
    0.23
    بوط
    0.22
    ⵡ
    0.22
     chemists
    0.22
    ették
    0.22
    ństw
    0.22
    𒂍
    0.21
    POSITIVE LOGITS
     =
    0.46
     ->
    0.44
    =
    0.42
     +
    0.41
    +
    0.41
     =>
    0.41
     ∈
    0.37
     →
    0.36
     ==
    0.36
     !=
    0.36
    Act Density 0.243%

    No Known Activations