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

    Neuronpedia

    INDEX
    Explanations

    project names and phases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     worst
    0.41
    problem
    0.40
    rit
    0.39
    ଯ
    0.39
    pool
    0.38
    кус
    0.38
     potente
    0.38
    processing
    0.37
     ruling
    0.37
    operand
    0.37
    POSITIVE LOGITS
     projects
    0.80
     Projects
    0.79
     progetti
    0.79
     projek
    0.78
    プロジェクト
    0.77
    Project
    0.76
     proyectos
    0.75
     projekt
    0.74
     проекты
    0.74
     پروژه
    0.74
    Act Density 0.014%

    No Known Activations