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

    Neuronpedia

    INDEX
    Explanations

    boxing and boxers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gru
    0.41
     البر
    0.41
     bytecode
    0.40
    盘
    0.39
    SAN
    0.38
    玩
    0.38
    Pending
    0.38
     snowboard
    0.38
     Align
    0.38
     பங்க
    0.38
    POSITIVE LOGITS
     boxer
    0.73
     boxers
    0.72
     boxing
    0.68
     boxe
    0.59
     Boxing
    0.58
     Boxer
    0.54
    🥊
    0.54
    boxing
    0.54
    Boxing
    0.52
    拳
    0.46
    Act Density 0.006%

    No Known Activations