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

    Neuronpedia

    INDEX
    Explanations

    asking to list things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toepassing
    0.57
    ر
    0.54
    层面
    0.54
     boje
    0.50
     Maschine
    0.49
     dingin
    0.49
    波动
    0.49
    ce
    0.49
     incarn
    0.49
     CMO
    0.49
    POSITIVE LOGITS
     list
    1.23
     список
    1.16
    list
    1.09
     lists
    1.00
    List
    0.99
    列表
    0.96
    LIST
    0.96
     списка
    0.96
     فہرست
    0.95
     List
    0.93
    Act Density 0.082%

    No Known Activations