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

    Neuronpedia

    INDEX
    Explanations

    tea or coffee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     THOR
    0.42
     Wies
    0.42
     Thor
    0.40
     Groß
    0.40
     Stockton
    0.39
     navigation
    0.39
     Navigation
    0.39
     Sunny
    0.39
     Knowles
    0.38
     elsewhere
    0.38
    POSITIVE LOGITS
    권
    0.47
    전문
    0.42
    ου
    0.41
    각
    0.39
    aux
    0.38
    etragen
    0.38
    燉
    0.38
    讒
    0.38
    cin
    0.38
    цена
    0.38
    Act Density 0.001%

    No Known Activations