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

    Neuronpedia

    INDEX
    Explanations

    connects "that" and "he"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vencedor
    0.38
     sucesso
    0.33
     успеха
    0.33
    为
    0.32
    purchase
    0.32
     успешно
    0.31
     incomple
    0.31
    入境
    0.31
    激动
    0.30
     успе
    0.30
    POSITIVE LOGITS
    ੫
    0.37
     Pener
    0.37
    ून्य
    0.35
    कीस
    0.35
     PPM
    0.35
    䡒
    0.35
    ්ර
    0.35
    CategoryID
    0.34
     കൊടു
    0.34
    bottomMargin
    0.34
    Act Density 0.001%

    No Known Activations