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

    Neuronpedia

    INDEX
    Explanations

    GUI designer professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wp
    0.42
     rif
    0.39
     aren
    0.38
     meses
    0.38
     añ
    0.38
     jp
    0.37
     dates
    0.36
    Ŵ
    0.36
     пред
    0.35
     기준으로
    0.35
    POSITIVE LOGITS
    设计师
    0.47
    学家
    0.46
    Localized
    0.43
     小物
    0.43
     Designer
    0.42
     designer
    0.41
     autonomy
    0.41
    浓度
    0.41
    nets
    0.41
    autoload
    0.41
    Act Density 0.001%

    No Known Activations