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

    Neuronpedia

    INDEX
    Explanations

    amusement park rides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    فاء
    0.87
    lucene
    0.83
     FILTER
    0.81
    屉
    0.79
     loaf
    0.79
     filter
    0.79
    FILTER
    0.79
     Filter
    0.78
    Filter
    0.77
    filter
    0.76
    POSITIVE LOGITS
    🎢
    1.88
    🎡
    1.61
     amusement
    1.58
    🎠
    1.50
     Amusement
    1.47
     vertigo
    1.33
     dizziness
    1.31
     carnival
    1.31
     rides
    1.30
     thrills
    1.27
    Act Density 0.223%

    No Known Activations