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

    Neuronpedia

    INDEX
    Explanations

    cherished relationships and memories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cmd
    0.77
     agress
    0.74
    恹
    0.73
    طبيق
    0.73
     softmax
    0.72
     agres
    0.72
     aggressiveness
    0.70
     perintah
    0.69
    commands
    0.68
    cmd
    0.68
    POSITIVE LOGITS
     memories
    2.07
     adventures
    1.92
     moments
    1.78
     experiences
    1.74
     joys
    1.73
     treasured
    1.72
     unforgettable
    1.70
     cherished
    1.66
     joy
    1.61
     Memories
    1.57
    Act Density 0.740%

    No Known Activations