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

    Neuronpedia

    INDEX
    Explanations

    action and adventure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cute
    0.40
    觀察
    0.40
     quirk
    0.40
     peculiarities
    0.39
     可愛
    0.39
    可愛
    0.38
    ubercul
    0.38
    妒
    0.38
    可愛い
    0.38
     subt
    0.37
    POSITIVE LOGITS
     action
    1.59
    action
    1.45
     एक्शन
    1.37
     thrilling
    1.35
     Action
    1.34
    Action
    1.32
     adrenaline
    1.28
     acción
    1.27
     exciting
    1.24
     ACTION
    1.23
    Act Density 0.061%

    No Known Activations