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

    Neuronpedia

    INDEX
    Explanations

    fall into or fall short

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ណ្ឌ
    0.42
     উঠছে
    0.40
    INFRINGEMENT
    0.38
    ગવાન
    0.38
     Gospels
    0.38
    тивного
    0.37
    ឡើង
    0.37
    )+"]
    0.36
    ренко
    0.36
    тивное
    0.36
    POSITIVE LOGITS
     fell
    1.05
     falling
    1.05
     falls
    1.01
     fall
    0.99
    Falling
    0.97
     Falling
    0.95
    落
    0.90
     fallen
    0.89
    fall
    0.89
     jatuh
    0.85
    Act Density 0.023%

    No Known Activations