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

    Neuronpedia

    INDEX
    Explanations

    missing someone's presence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liked
    0.46
     separation
    0.42
     loved
    0.41
    tok
    0.40
     প্রিয়
    0.40
     Separation
    0.40
     wodurch
    0.40
     separated
    0.40
     séparation
    0.39
     dù
    0.38
    POSITIVE LOGITS
     forever
    0.53
     hereafter
    0.53
    จะไม่
    0.47
     henceforth
    0.46
    hereafter
    0.43
     hereinafter
    0.42
    forever
    0.42
     nebude
    0.42
    明年
    0.42
     जाईल
    0.41
    Act Density 0.002%

    No Known Activations