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

    Neuronpedia

    INDEX
    Explanations

    feel

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Feeling
    0.81
     feeling
    0.76
     Feel
    0.74
    feeling
    0.70
    Feeling
    0.70
     feel
    0.68
    Feel
    0.66
    感じ
    0.61
     feels
    0.59
    feel
    0.58
    POSITIVE LOGITS
     compelled
    0.91
     obligated
    0.85
     overwhelmed
    0.80
     empowered
    0.80
     pressured
    0.80
     cheated
    0.79
     guilty
    0.77
     comforted
    0.75
     like
    0.75
     reassured
    0.72
    Act Density 0.123%

    No Known Activations