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

    Neuronpedia

    INDEX
    Explanations

    European Parliament

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     republik
    0.55
     tật
    0.54
     YANG
    0.54
    ウッド
    0.53
     GOP
    0.53
     assinatura
    0.53
     pogod
    0.52
     RECEIPTS
    0.52
     stanie
    0.52
     scorched
    0.52
    POSITIVE LOGITS
     소비
    0.66
    消费
    0.59
    carotene
    0.59
    ignores
    0.59
     appreci
    0.58
     pancre
    0.58
    consumption
    0.57
    MouseDown
    0.57
    Ein
    0.55
     consumption
    0.55
    Act Density 0.001%

    No Known Activations