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

    Neuronpedia

    INDEX
    Explanations

    URLs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.35
     ruling
    0.35
     striving
    0.32
    ,
    0.32
     foundational
    0.31
     strides
    0.29
     advancements
    0.29
     PartialEq
    0.29
     🌱
    0.29
     –
    0.29
    POSITIVE LOGITS
     जानिए
    0.31
    ሳሪያ
    0.29
    totime
    0.29
     dukkham
    0.28
    followlike
    0.27
    시스템
    0.27
     कंडिशनर
    0.27
    akaranam
    0.27
     plufieurs
    0.27
    abbanti
    0.27
    Act Density 0.030%

    No Known Activations