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

    Neuronpedia

    INDEX
    Explanations

    YAML configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     情况
    0.80
     東京
    0.69
     사이즈
    0.68
    调整
    0.68
    形势
    0.66
     innan
    0.66
     nokta
    0.66
    ೀಲ
    0.66
    Wrist
    0.65
    넣
    0.65
    POSITIVE LOGITS
    title
    0.91
    ENA
    0.77
    AME
    0.77
    author
    0.76
    UID
    0.74
    TAL
    0.71
    HG
    0.71
     HM
    0.70
     title
    0.70
    Title
    0.69
    Act Density 0.017%

    No Known Activations