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

    Neuronpedia

    INDEX
    Explanations

    Azure AD authentication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CIRCLE
    0.42
    టమి
    0.38
     Vign
    0.38
     제외
    0.37
    ższ
    0.36
     Pros
    0.36
    leqq
    0.36
    ंबल
    0.35
    Ping
    0.35
     Bucket
    0.35
    POSITIVE LOGITS
     graphs
    0.44
    Graph
    0.44
     graph
    0.43
     Graph
    0.43
     MSA
    0.40
    graphs
    0.38
    MSA
    0.38
    Zara
    0.38
    باب
    0.37
     ECA
    0.37
    Act Density 0.008%

    No Known Activations