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

    Neuronpedia

    INDEX
    Explanations

    Cold War

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ینو
    0.75
    ación
    0.68
    ë
    0.68
    abhave
    0.65
    ings
    0.64
    ो
    0.64
    ンの
    0.62
    ән
    0.62
    ations
    0.61
    owaną
    0.61
    POSITIVE LOGITS
     Cold
    0.80
     Vietnam
    0.70
     frío
    0.69
     about
    0.68
     vodka
    0.68
     espionage
    0.68
     fifties
    0.68
     to
    0.66
     chilly
    0.63
     pantry
    0.63
    Act Density 0.013%

    No Known Activations