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

    Neuronpedia

    INDEX
    Explanations

    Soviet Era history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Being
    0.46
     Levi
    0.42
     washers
    0.42
     shirts
    0.41
     transporte
    0.41
     Militar
    0.41
     Grazie
    0.41
     Without
    0.40
    rentes
    0.40
    blogs
    0.39
    POSITIVE LOGITS
    न
    0.49
    解答
    0.43
     spät
    0.42
    解决
    0.42
    踵
    0.42
    Modular
    0.41
    𝗗
    0.40
    的基本
    0.40
    IND
    0.40
    Vlad
    0.40
    Act Density 0.005%

    No Known Activations