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

    Neuronpedia

    INDEX
    Explanations

    explaining or describing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reserved
    0.84
     strewn
    0.73
     reserving
    0.66
    reserved
    0.64
    发现
    0.63
    Reserved
    0.62
    حاء
    0.61
     soggy
    0.61
     पढ़ाया
    0.60
     встречаются
    0.60
    POSITIVE LOGITS
     explain
    2.73
     Explain
    2.70
    Explain
    2.53
    explain
    2.45
     describe
    2.39
     Describe
    2.36
    Describe
    2.22
     explicar
    2.19
     explaining
    2.17
    describe
    2.15
    Act Density 0.702%

    No Known Activations