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

    Neuronpedia

    INDEX
    Explanations

    expressing appreciation or gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Warning
    0.71
    warning
    0.69
     Favorite
    0.68
    WARNING
    0.67
     fulfilment
    0.67
     Controversy
    0.66
     SUCCESSFULLY
    0.66
     interchangeably
    0.66
    Warning
    0.66
     unfavourable
    0.66
    POSITIVE LOGITS
     appreciate
    2.73
     appreciated
    2.52
     appreciates
    2.38
     appreciation
    2.22
    appreciated
    2.22
    appreci
    2.19
     appreciating
    2.07
     apreci
    2.02
     appreci
    1.96
     appreciative
    1.95
    Act Density 0.150%

    No Known Activations