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

    Neuronpedia

    INDEX
    Explanations

    unspoken feelings and sensations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     weeping
    0.57
     wept
    0.57
     weep
    0.53
     grieving
    0.53
    呱
    0.49
     vomiting
    0.49
     cryogenic
    0.47
     शोक
    0.46
     inspirational
    0.44
     ঘৃ
    0.44
    POSITIVE LOGITS
     unspoken
    0.70
     tension
    0.65
     warmth
    0.55
     tensión
    0.55
     atmosphere
    0.55
     closeness
    0.55
     proximity
    0.54
    紧张
    0.54
     intimacy
    0.53
     embarrassment
    0.52
    Act Density 0.040%

    No Known Activations