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

    Neuronpedia

    INDEX
    Explanations

    United / Labour Party

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지로
    1.38
    1.34
     إنه
    1.22
    주고
    1.21
    м
    1.18
    وط
    1.17
    propelled
    1.17
    わからない
    1.14
    空的
    1.13
    élevage
    1.12
    POSITIVE LOGITS
    𝑎
    1.59
     indicadores
    1.59
    skjaer
    1.59
    𝕒
    1.59
     painkillers
    1.55
    𝑖
    1.55
     inefficiencies
    1.53
    𝑂
    1.52
    ात
    1.48
    ్
    1.47
    Act Density 0.001%

    No Known Activations