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

    Neuronpedia

    INDEX
    Explanations

    security and peace agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    entum
    0.44
    ፫
    0.43
     narzęd
    0.43
     httpClient
    0.42
     GridPane
    0.42
    язви
    0.42
    btnLogin
    0.41
    ജ്യ
    0.41
    jetbrains
    0.40
     开发
    0.40
    POSITIVE LOGITS
     ceasefire
    0.79
     peacekeeping
    0.77
     observers
    0.64
     truce
    0.64
    monitoring
    0.64
     monitoring
    0.63
     observer
    0.62
     verification
    0.62
     Verification
    0.58
    verification
    0.57
    Act Density 0.006%

    No Known Activations