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

    Neuronpedia

    INDEX
    Explanations

    peace and reconciliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভাগ্য
    0.45
     अनियमित
    0.45
     भाग्य
    0.43
    odymium
    0.43
    ResultSet
    0.43
     excitement
    0.42
     zuverläss
    0.42
     Aufmerksamkeit
    0.41
    ⚡
    0.41
     Vertex
    0.41
    POSITIVE LOGITS
     reconciliation
    1.62
     reconc
    1.52
     concili
    1.48
     Reconciliation
    1.40
     peaceful
    1.31
     peace
    1.30
    conciliation
    1.30
     peac
    1.28
     reconcile
    1.26
     peacefully
    1.23
    Act Density 0.022%

    No Known Activations