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

    Neuronpedia

    INDEX
    Explanations

    value chain and accrual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を表示
    1.10
    を入力
    0.98
    lapse
    0.96
    ligne
    0.95
    la
    0.95
    lice
    0.94
    weaving
    0.94
    oubtedly
    0.94
    ം
    0.92
    手
    0.91
    POSITIVE LOGITS
     aggiunto
    1.55
     tambah
    1.46
    एशन
    1.41
    वान
    1.31
     Proposition
    1.28
     ajout
    1.25
     proposition
    1.24
     madres
    1.19
     किलो
    1.11
     mobili
    1.10
    Act Density 0.150%

    No Known Activations