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

    Neuronpedia

    INDEX
    Explanations

    saying thank you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    纖
    0.40
     sparsebundle
    0.38
     flamb
    0.38
     ib
    0.38
     γρα
    0.38
     concatenate
    0.37
    可谓
    0.37
     nécess
    0.37
     argomento
    0.37
     Worse
    0.37
    POSITIVE LOGITS
     thank
    0.85
     Thank
    0.77
    Thank
    0.77
    感谢
    0.74
     thanking
    0.71
     THANK
    0.70
     profusely
    0.70
    THANK
    0.70
     спасибо
    0.69
    谢谢
    0.69
    Act Density 0.010%

    No Known Activations