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

    Neuronpedia

    INDEX
    Explanations

    distress and emotional reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cheerfully
    0.51
    惦
    0.50
     grinned
    0.49
     chuckled
    0.49
     enthusi
    0.47
     bragging
    0.46
     wink
    0.46
     happily
    0.46
    好奇
    0.46
     grinning
    0.45
    POSITIVE LOGITS
    💔
    0.77
     heartbreaking
    0.76
     tears
    0.73
     angu
    0.73
     distraught
    0.73
     hopelessness
    0.71
    痛苦
    0.71
     despair
    0.69
     heartbroken
    0.69
     sobbing
    0.68
    Act Density 0.057%

    No Known Activations