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

    Neuronpedia

    INDEX
    Explanations

    settle down or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     set
    0.65
     setup
    0.60
     Set
    0.54
     setting
    0.54
    设置
    0.54
    セット
    0.51
     Sets
    0.51
     settings
    0.50
     sets
    0.50
    設定
    0.50
    POSITIVE LOGITS
    Sett
    0.62
     disputes
    0.57
    sett
    0.55
     nervioso
    0.53
     nerves
    0.52
     settle
    0.50
     settling
    0.50
     settles
    0.49
    Feeling
    0.48
     doubts
    0.48
    Act Density 0.006%

    No Known Activations