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

    Neuronpedia

    INDEX
    Explanations

    emotions and reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dependability
    0.76
    reliability
    0.74
     linearity
    0.74
     Consistency
    0.73
     consistency
    0.70
    稳定性
    0.70
     Availability
    0.69
    Consistency
    0.69
     stability
    0.69
    stability
    0.69
    POSITIVE LOGITS
     amusement
    0.96
     dismay
    0.80
     growing
    0.78
     surprise
    0.78
     mixture
    0.78
     mingled
    0.77
     bew
    0.77
     chagrin
    0.74
     disgust
    0.73
     distaste
    0.70
    Act Density 0.162%

    No Known Activations