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

    Neuronpedia

    INDEX
    Explanations

    emotional intimacy and connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     context
    0.54
     concentration
    0.52
     angular
    0.49
     two
    0.49
     ven
    0.48
     platforms
    0.48
     arc
    0.47
     subject
    0.46
     react
    0.46
     sites
    0.46
    POSITIVE LOGITS
    ؟!
    0.57
    ！”
    0.55
    Ру
    0.53
    Но
    0.53
    Про
    0.52
     завжди
    0.52
     чтоб
    0.52
     اکبر
    0.51
    Все
    0.50
    Truly
    0.50
    Act Density 0.001%

    No Known Activations