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

    Neuronpedia

    INDEX
    Explanations

    awe, amazement, fascination, admiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sukh
    0.77
     <!--<
    0.72
     unpleasant
    0.67
     undesirable
    0.64
     nonatomic
    0.63
    🙅
    0.62
    ńskiej
    0.62
     Redox
    0.62
     suicide
    0.62
    ໂ
    0.61
    POSITIVE LOGITS
     awe
    2.46
     amazement
    2.07
     admiration
    1.99
     wonder
    1.94
     amazed
    1.89
     marvel
    1.88
     aw
    1.84
     fascination
    1.76
     fascinated
    1.72
     astonishment
    1.65
    Act Density 0.222%

    No Known Activations