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

    Neuronpedia

    INDEX
    Explanations

    how something feels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ष्‍ट
    0.36
    usercontent
    0.35
    luent
    0.35
     Lookup
    0.35
     તમારે
    0.35
    िज्या
    0.34
    葲
    0.34
    lookup
    0.33
    "+"|".
    0.33
    èdent
    0.32
    POSITIVE LOGITS
     feel
    3.89
     feels
    3.73
     feeling
    3.67
    feel
    3.64
    Feel
    3.59
     Feel
    3.56
    感觉
    3.48
    feels
    3.39
     FEEL
    3.39
    feeling
    3.38
    Act Density 0.398%

    No Known Activations