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

    Neuronpedia

    INDEX
    Explanations

    mentions of war and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    war and its consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ateri
    -0.46
     jScrollPane
    -0.46
    cida
    -0.44
     Schulter
    -0.43
    JsonInclude
    -0.43
     Clair
    -0.43
    "])
    -0.42
    ople
    -0.41
    utie
    -0.41
    sieh
    -0.41
    POSITIVE LOGITS
     war
    1.40
     guerra
    1.29
     oorlog
    1.23
     guerre
    1.22
     War
    1.21
    War
    1.12
     savaş
    1.10
     Krieg
    1.09
     WAR
    1.08
     krig
    1.05
    Act Density 0.030%

    No Known Activations